subject:(Natural language processing)

University of Georgia

1. Boisclair, William Cody. SYCORAX: an automated analyzer of the syntactic complexity of English text.

Degree: PhD, Computer Science, 2011, University of Georgia

URL: http://purl.galileo.usg.edu/uga_etd/boisclair_william_c_201108_phd

► This dissertation describes the development and evaluation of a new analyzer for syntactic complexity known as SYCORAX: the SYntactic COmplexity RAting eXpert. SYCORAX, like several… (more)

▼ This dissertation describes the development and evaluation of a new analyzer for syntactic complexity known as SYCORAX: the SYntactic COmplexity RAting eXpert. SYCORAX, like several prior applications for automated analysis of syntactic complexity (e.g., Long et al., 2006; Channell, 2007; MacWhinney, 2011), is based on the Developmental Sentence Scoring (DSS) scale developed by Lee (1974). These existing applications, however, all have one significant limitation in common: they are all strictly based on immediate linear context within a sentence. It is evident from prior work (Channell, 2003; Judson, 2006) that certain syntactic structures involved in DSS are simply not apparent from linear context alone; indeed, many structures incorrectly analyzed by human raters are due to incorrect interpretation of local context (Lively, 1984). In contrast, SYCORAX incorporates a newly-developed shallow dependency parser known as JED (Just Enough Dependency) optimized for the dependencies which are important in DSS, and uses the resulting parse tree in the calculation of its DSS scores. Even without complete optimization of its DSS rules, the use of shallow parsing in SYCORAX produces a distinct overall boost in the accuracy of syntactic complexity scores on a variety of manually-scored real-world transcripts, as measured using Pearson correlation coefficient and point-by-point accuracy, with no significant increase in execution time. DSS has proven numerous times to be psycholinguistically valid. It was originally designed to identify language delays in children, and more recent experiments have found it to still be valid in that respect (e.g., Scarborough, 1990); in addition, it has been found to be of use in identifying language decline in adults (Cheung and Kemper, 1992; Kemper et al., 2003, 2004), distinguishing different forms of developmental delay (Finestack and Abbeduto, 2010), and even identifying Alzheimer’s dementia (Kemper et al., 1993). It is believed that the improvement in its automated analysis by SYCORAX will prompt even further research regarding it, much as the prior project CPIDR (Brown et al., 2008) has done for semantic complexity (Covington et al., 2009; Jarrold et al., 2010; Engelman et al., 2010; Tsai, 2010). Advisors/Committee Members: Walter D. Potter.

Subjects/Keywords: Natural language processing

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Boisclair, W. C. (2011). SYCORAX: an automated analyzer of the syntactic complexity of English text. (Doctoral Dissertation). University of Georgia. Retrieved from http://purl.galileo.usg.edu/uga_etd/boisclair_william_c_201108_phd

Chicago Manual of Style (16^th Edition):

Boisclair, William Cody. “SYCORAX: an automated analyzer of the syntactic complexity of English text.” 2011. Doctoral Dissertation, University of Georgia. Accessed February 22, 2020. http://purl.galileo.usg.edu/uga_etd/boisclair_william_c_201108_phd.

MLA Handbook (7^th Edition):

Boisclair, William Cody. “SYCORAX: an automated analyzer of the syntactic complexity of English text.” 2011. Web. 22 Feb 2020.

Vancouver:

Boisclair WC. SYCORAX: an automated analyzer of the syntactic complexity of English text. [Internet] [Doctoral dissertation]. University of Georgia; 2011. [cited 2020 Feb 22]. Available from: http://purl.galileo.usg.edu/uga_etd/boisclair_william_c_201108_phd.

Council of Science Editors:

Boisclair WC. SYCORAX: an automated analyzer of the syntactic complexity of English text. [Doctoral Dissertation]. University of Georgia; 2011. Available from: http://purl.galileo.usg.edu/uga_etd/boisclair_william_c_201108_phd

Anna University

2. Balaji J. Pattern based bootstrapping approaches For natural language processing of Morphologically rich languages;.

Degree: Pattern based bootstrapping approaches For natural language processing of Morphologically rich languages, 2015, Anna University

URL: http://shodhganga.inflibnet.ac.in/handle/10603/35514

►

This thesis attempts to tackle Natural Language Processing NLP tasks by exploiting the special characteristics of morphologically rich newlineLanguages In this thesis we use Tamil… (more)

Subjects/Keywords: Natural Language Processing

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

J, B. (2015). Pattern based bootstrapping approaches For natural language processing of Morphologically rich languages;. (Thesis). Anna University. Retrieved from http://shodhganga.inflibnet.ac.in/handle/10603/35514

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

J, Balaji. “Pattern based bootstrapping approaches For natural language processing of Morphologically rich languages;.” 2015. Thesis, Anna University. Accessed February 22, 2020. http://shodhganga.inflibnet.ac.in/handle/10603/35514.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

J, Balaji. “Pattern based bootstrapping approaches For natural language processing of Morphologically rich languages;.” 2015. Web. 22 Feb 2020.

Vancouver:

J B. Pattern based bootstrapping approaches For natural language processing of Morphologically rich languages;. [Internet] [Thesis]. Anna University; 2015. [cited 2020 Feb 22]. Available from: http://shodhganga.inflibnet.ac.in/handle/10603/35514.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

J B. Pattern based bootstrapping approaches For natural language processing of Morphologically rich languages;. [Thesis]. Anna University; 2015. Available from: http://shodhganga.inflibnet.ac.in/handle/10603/35514

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

3. Konstas, Ioannis. Joint models for concept-to-text generation.

Degree: PhD, 2014, University of Edinburgh

URL: http://hdl.handle.net/1842/8926

► Much of the data found on the world wide web is in numeric, tabular, or other nontextual format (e.g., weather forecast tables, stock market charts,… (more)

▼ Much of the data found on the world wide web is in numeric, tabular, or other nontextual format (e.g., weather forecast tables, stock market charts, live sensor feeds), and thus inaccessible to non-experts or laypersons. However, most conventional search engines and natural language processing tools (e.g., summarisers) can only handle textual input. As a result, data in non-textual form remains largely inaccessible. Concept-to-text generation refers to the task of automatically producing textual output from non-linguistic input, and holds promise for rendering non-linguistic data widely accessible. Several successful generation systems have been produced in the past twenty years. They mostly rely on human-crafted rules or expert-driven grammars, implement a pipeline architecture, and usually operate in a single domain. In this thesis, we present several novel statistical models that take as input a set of database records and generate a description of them in natural language text. Our unique idea is to combine the processes of structuring a document (document planning), deciding what to say (content selection) and choosing the specific words and syntactic constructs specifying how to say it (lexicalisation and surface realisation), in a uniform joint manner. Rather than breaking up the generation process into a sequence of local decisions, we define a probabilistic context-free grammar that globally describes the inherent structure of the input (a corpus of database records and text describing some of them). This joint representation allows individual processes (i.e., document planning, content selection, and surface realisation) to communicate and influence each other naturally. We recast generation as the task of finding the best derivation tree for a set of input database records and our grammar, and describe several algorithms for decoding in this framework that allows to intersect the grammar with additional information capturing fluency and syntactic well-formedness constraints. We implement our generators using the hypergraph framework. Contrary to traditional systems, we learn all the necessary document, structural and linguistic knowledge from unannotated data. Additionally, we explore a discriminative reranking approach on the hypergraph representation of our model, by including more refined content selection features. Central to our approach is the idea of porting our models to various domains; we experimented on four widely different domains, namely sportscasting, weather forecast generation, booking flights, and troubleshooting guides. The performance of our systems is competitive and often superior compared to state-of-the-art systems that use domain specific constraints, explicit feature engineering or labelled data.

Subjects/Keywords: 006.3; natural language generation; natural language processing

10 more images…

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Konstas, I. (2014). Joint models for concept-to-text generation. (Doctoral Dissertation). University of Edinburgh. Retrieved from http://hdl.handle.net/1842/8926

Chicago Manual of Style (16^th Edition):

Konstas, Ioannis. “Joint models for concept-to-text generation.” 2014. Doctoral Dissertation, University of Edinburgh. Accessed February 22, 2020. http://hdl.handle.net/1842/8926.

MLA Handbook (7^th Edition):

Konstas, Ioannis. “Joint models for concept-to-text generation.” 2014. Web. 22 Feb 2020.

Vancouver:

Konstas I. Joint models for concept-to-text generation. [Internet] [Doctoral dissertation]. University of Edinburgh; 2014. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/1842/8926.

Council of Science Editors:

Konstas I. Joint models for concept-to-text generation. [Doctoral Dissertation]. University of Edinburgh; 2014. Available from: http://hdl.handle.net/1842/8926

4. Irvine, Ann. Using Comparable Corpora to Augment Statistical Machine Translation Models in Low Resource Settings.

Degree: 2014, Johns Hopkins University

URL: http://jhir.library.jhu.edu/handle/1774.2/38018

► Previously, statistical machine translation (SMT) models have been estimated from parallel corpora, or pairs of translated sentences. In this thesis, we directly incorporate comparable corpora… (more)

▼ Previously, statistical machine translation (SMT) models have been estimated from parallel corpora, or pairs of translated sentences. In this thesis, we directly incorporate comparable corpora into the estimation of end-to-end SMT models. In contrast to parallel corpora, comparable corpora are pairs of monolingual corpora that have some cross-lingual similarities, for example topic or publication date, but that do not necessarily contain any direct translations. Comparable corpora are more readily available in large quantities than parallel corpora, which require significant human effort to compile. We use comparable corpora to estimate machine translation model parameters and show that doing so improves performance in settings where a limited amount of parallel data is available for training. The major contributions of this thesis are the following: * We release ‘language packs’ for 151 human languages, which include bilingual dictionaries, comparable corpora of Wikipedia document pairs, comparable corpora of time-stamped news text that we harvested from the web, and, for non-roman script languages, dictionaries of name pairs, which are likely to be transliterations. * We present a novel technique for using a small number of example word translations to learn a supervised model for bilingual lexicon induction which takes advantage of a wide variety of signals of translation equivalence that can be estimated over comparable corpora. * We show that using comparable corpora to induce new translations and estimate new phrase table feature functions improves end-to-end statistical machine translation performance for low resource language pairs as well as domains. * We present a novel algorithm for composing multiword phrase translations from multiple unigram translations and then use comparable corpora to prune the large space of hypothesis translations. We show that these induced phrase translations improve machine translation performance beyond that of component unigrams. This thesis focuses on critical low resource machine translation settings, where insufficient parallel corpora exist for training statistical models. We experiment with both low resource language pairs and low resource domains of text. We present results from our novel error analysis methodology, which show that most translation errors in low resource settings are due to unseen source language words and phrases and unseen target language translations. We also find room for fixing errors due to how different translations are weighted, or scored, in the models. We target both error types; we use comparable corpora to induce new word and phrase translations and estimate novel translation feature scores. Our experiments show that augmenting baseline SMT systems with new translations and features estimated over comparable corpora improves translation performance significantly. Additionally, our techniques expand the applicability of statistical machine translation to those language pairs for which zero parallel text is available. Advisors/Committee Members: Callison-Burch, Chris (advisor).

Subjects/Keywords: machine translation; natural language processing

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Irvine, A. (2014). Using Comparable Corpora to Augment Statistical Machine Translation Models in Low Resource Settings. (Thesis). Johns Hopkins University. Retrieved from http://jhir.library.jhu.edu/handle/1774.2/38018

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Irvine, Ann. “Using Comparable Corpora to Augment Statistical Machine Translation Models in Low Resource Settings.” 2014. Thesis, Johns Hopkins University. Accessed February 22, 2020. http://jhir.library.jhu.edu/handle/1774.2/38018.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Irvine, Ann. “Using Comparable Corpora to Augment Statistical Machine Translation Models in Low Resource Settings.” 2014. Web. 22 Feb 2020.

Vancouver:

Irvine A. Using Comparable Corpora to Augment Statistical Machine Translation Models in Low Resource Settings. [Internet] [Thesis]. Johns Hopkins University; 2014. [cited 2020 Feb 22]. Available from: http://jhir.library.jhu.edu/handle/1774.2/38018.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Irvine A. Using Comparable Corpora to Augment Statistical Machine Translation Models in Low Resource Settings. [Thesis]. Johns Hopkins University; 2014. Available from: http://jhir.library.jhu.edu/handle/1774.2/38018

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Hong Kong

5. 周春婷; Zhou, Chunting. Representation learning for natural language processing.

Degree: M. Phil., 2016, University of Hong Kong

URL: http://hdl.handle.net/10722/236583

►

Many applications in natural language processing (NLP) depend on extracting compact and informative features from unstructured texts. Distributed representations encode data as continuous vectors, by… (more)

▼

Many applications in natural language processing (NLP) depend on extracting compact and informative features from unstructured texts. Distributed representations encode data as continuous vectors, by constructing a projection from semantics to points in high dimensional spaces. As an effective and efficient way of learning such representations, neural network based models have obtained great successes in various NLP applications. For different NLP scenarios, different types of neural networks can be carefully assembled to mimic human's behavioral patterns of understanding the real world or to exploit the semantics based on linguistic composition. This thesis focuses on representation learning at different granularities; different neural network models are designed that embed features of words, sentences and articles. Learned representations are applied in three selected natural language applications: sentiment classification, text classification and reading comprehension. The first part of this work learns word representations with a shallow neural network, in which global topical knowledge is incorporated into local contexts when a word interacts with its context words. The learned word vectors are evaluated on three tasks: word analogical reasoning, word similarity task and text classification. Experiments show that word embeddings are enhanced in terms of preserving their semantic information together with category knowledge. The second part of this work proposes a model called \C-LSTM" which can learn sentence representations through combining a convolutional neural network (CNN) and a long short-term memory (LSTM) recurrent neural network. The input to the LSTM network is sequential n-gram features extracted by the CNN, and thus at each time step the input has integrated a wide range of context information. Experiments on sentiment classification and question-type classification tasks demonstrate the remarkable performance of C-LSTM as compared with state-of-the-art models. The last part of this work proposes a context aware attention neural network model for reading comprehension. Two separate convolutional neural networks are employed to encode the articles, and the max pooling result of one CNN is used to attentively read the other CNN output. The attended representation of the article together with the query representation are used to predict the answer. Extensive experimental analyses have verified its effectiveness in extracting informative n-grams that match the query or are helpful to answer inference.

published_or_final_version

Computer Science

Master

Master of Philosophy

Subjects/Keywords: Natural language processing (Computer science)

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

周春婷; Zhou, C. (2016). Representation learning for natural language processing. (Masters Thesis). University of Hong Kong. Retrieved from http://hdl.handle.net/10722/236583

Chicago Manual of Style (16^th Edition):

周春婷; Zhou, Chunting. “Representation learning for natural language processing.” 2016. Masters Thesis, University of Hong Kong. Accessed February 22, 2020. http://hdl.handle.net/10722/236583.

MLA Handbook (7^th Edition):

周春婷; Zhou, Chunting. “Representation learning for natural language processing.” 2016. Web. 22 Feb 2020.

Vancouver:

周春婷; Zhou C. Representation learning for natural language processing. [Internet] [Masters thesis]. University of Hong Kong; 2016. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/10722/236583.

Council of Science Editors:

周春婷; Zhou C. Representation learning for natural language processing. [Masters Thesis]. University of Hong Kong; 2016. Available from: http://hdl.handle.net/10722/236583

University of Minnesota

6. Exley, Andrew. Improvements to a Speech Repair Parser.

Degree: PhD, Computer Science, 2016, University of Minnesota

URL: http://hdl.handle.net/11299/181724

► Parsing is a common task for speech-recognition systems, but many parsers ignore the possibility of speech errors and repairs, which are very common in conversational… (more)

Subjects/Keywords: Natural Language Processing; Parsing

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Exley, A. (2016). Improvements to a Speech Repair Parser. (Doctoral Dissertation). University of Minnesota. Retrieved from http://hdl.handle.net/11299/181724

Chicago Manual of Style (16^th Edition):

Exley, Andrew. “Improvements to a Speech Repair Parser.” 2016. Doctoral Dissertation, University of Minnesota. Accessed February 22, 2020. http://hdl.handle.net/11299/181724.

MLA Handbook (7^th Edition):

Exley, Andrew. “Improvements to a Speech Repair Parser.” 2016. Web. 22 Feb 2020.

Vancouver:

Exley A. Improvements to a Speech Repair Parser. [Internet] [Doctoral dissertation]. University of Minnesota; 2016. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/11299/181724.

Council of Science Editors:

Exley A. Improvements to a Speech Repair Parser. [Doctoral Dissertation]. University of Minnesota; 2016. Available from: http://hdl.handle.net/11299/181724

7. Choe, Do Kook. Toward Solving Penn Treebank Parsing.

Degree: Department of Computer Science, 2017, Brown University

URL: https://repository.library.brown.edu/studio/item/bdr:733298/

► A natural language parser recovers the latent grammatical structures of sentences. In many natural language processing (NLP) applications, parsing is applied to sentences first and… (more)

Subjects/Keywords: Natural language processing (Computer science)

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Choe, D. K. (2017). Toward Solving Penn Treebank Parsing. (Thesis). Brown University. Retrieved from https://repository.library.brown.edu/studio/item/bdr:733298/

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Choe, Do Kook. “Toward Solving Penn Treebank Parsing.” 2017. Thesis, Brown University. Accessed February 22, 2020. https://repository.library.brown.edu/studio/item/bdr:733298/.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Choe, Do Kook. “Toward Solving Penn Treebank Parsing.” 2017. Web. 22 Feb 2020.

Vancouver:

Choe DK. Toward Solving Penn Treebank Parsing. [Internet] [Thesis]. Brown University; 2017. [cited 2020 Feb 22]. Available from: https://repository.library.brown.edu/studio/item/bdr:733298/.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Choe DK. Toward Solving Penn Treebank Parsing. [Thesis]. Brown University; 2017. Available from: https://repository.library.brown.edu/studio/item/bdr:733298/

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Ryerson University

8. Krezolek, Michal Andrzej. Natural Language Learning.

Degree: 2010, Ryerson University

URL: https://digital.library.ryerson.ca/islandora/object/RULA%3A635

► This thesis is a small step towards automated learning of natural languages. With the use of a parser that incorporates machine-learning algorithms, our algorithm is… (more)

Subjects/Keywords: Natural language processing; Machine learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Krezolek, M. A. (2010). Natural Language Learning. (Thesis). Ryerson University. Retrieved from https://digital.library.ryerson.ca/islandora/object/RULA%3A635

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Krezolek, Michal Andrzej. “Natural Language Learning.” 2010. Thesis, Ryerson University. Accessed February 22, 2020. https://digital.library.ryerson.ca/islandora/object/RULA%3A635.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Krezolek, Michal Andrzej. “Natural Language Learning.” 2010. Web. 22 Feb 2020.

Vancouver:

Krezolek MA. Natural Language Learning. [Internet] [Thesis]. Ryerson University; 2010. [cited 2020 Feb 22]. Available from: https://digital.library.ryerson.ca/islandora/object/RULA%3A635.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Krezolek MA. Natural Language Learning. [Thesis]. Ryerson University; 2010. Available from: https://digital.library.ryerson.ca/islandora/object/RULA%3A635

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Victoria

9. Sedghi, Elham. A novel stroke prediction model based on clinical natural language processing (NLP) and data mining methods.

Degree: Department of Computer Science, 2017, University of Victoria

URL: http://hdl.handle.net/1828/7879

► Early detection and treatment of stroke can save lives. Before any procedure is planned, the patient is traditionally subjected to a brain scan such as… (more)

▼ Early detection and treatment of stroke can save lives. Before any procedure is planned, the patient is traditionally subjected to a brain scan such as Magnetic Resonance Imaging (MRI) in order to make sure he/she receives a safe treatment. Before any imaging is performed, the patient is checked into Emergency Room (ER) and clinicians from the Stroke Rapid Assessment Unit (SRAU) perform an evaluation of the patient's signs and symptoms. The question we address in this thesis is: Can Data Mining (DM) algorithms be employed to reliably predict the occurrence of stroke in a patient based on the signs and symptoms gathered by the clinicians and other staff in the ER or the SRAU? A reliable DM algorithm would be very useful in helping the clinicians make a better decision whether to escalate the case or classify it as a non-life threatening mimic and not put the patient through unnecessary imaging and tests. Such an algorithm would not only make the life of patients and clinicians easier but would also enable the hospitals to cut down on their costs. Most of the signs and symptoms gathered by clinicians in the ER or the SRAU are stored in free-text format in hospital information systems. Using techniques from Natural Language Processing (NLP), the vocabularies of interest can be extracted and classiffied. A big challenge in this process is that medical narratives are full of misspelled words and clinical abbreviations. It is a well known fact that the quality of data mining results crucially depends on the quality of input data. In this thesis, as a rst contribution, we describe a procedure to preprocess the raw data and transform it into clean, well-structured data that can be effectively used by DM learning algorithms. Another contribution of this thesis is producing a set of carefully crafted rules to perform detection of negated meaning in free-text sentences. Using these rules, we were able to get the correct semantics of sentences and provide much more useful datasets to DM learning algorithms. This thesis consists of three main parts. In the first part, we focus on building classi ers to reliably distinguish stroke and Transient Ischemic Attack (TIA) from mimic cases. For this, we used text extracted from the "chief complaint" and "history of patient illness" fields available in the patients' les at the Victoria General Hospital (VGH). In collaboration with stroke specialists, we identified a well-de ned set of stroke-related keywords. Next, we created practical tools to accurately assign keywords from this set to each patient. Then, we performed extensive experiments for nding the right learning algorithm to build the best classifier that provides a good balance between sensitivity, specificity, and a host of other quality indicators. In the second part, we focus on the most important mimic case, migraine, and how to e ectively distinguish it from stroke or TIA. This is a challenging problem because migraine has many signs and symptoms that are similar to those of stroke or TIA. Another challenge we address is… Advisors/Committee Members: Thomo, Alex (supervisor), Weber, Jens H. (supervisor).

Subjects/Keywords: Data Mining; Natural Language Processing

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Sedghi, E. (2017). A novel stroke prediction model based on clinical natural language processing (NLP) and data mining methods. (Thesis). University of Victoria. Retrieved from http://hdl.handle.net/1828/7879

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Sedghi, Elham. “A novel stroke prediction model based on clinical natural language processing (NLP) and data mining methods.” 2017. Thesis, University of Victoria. Accessed February 22, 2020. http://hdl.handle.net/1828/7879.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Sedghi, Elham. “A novel stroke prediction model based on clinical natural language processing (NLP) and data mining methods.” 2017. Web. 22 Feb 2020.

Vancouver:

Sedghi E. A novel stroke prediction model based on clinical natural language processing (NLP) and data mining methods. [Internet] [Thesis]. University of Victoria; 2017. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/1828/7879.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Sedghi E. A novel stroke prediction model based on clinical natural language processing (NLP) and data mining methods. [Thesis]. University of Victoria; 2017. Available from: http://hdl.handle.net/1828/7879

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Virginia Tech

10. Kakusa, Takondwa Lisungu. Use of Assembly Inspired Instructions in the Allowance of Natural Language Processing in ROS.

Degree: MS, Electrical and Computer Engineering, 2018, Virginia Tech

URL: http://hdl.handle.net/10919/84521

► Natural Language processing is a growing field and widely used in both industrial and and commercial cases. Though it is difficult to create a natural… (more)

Subjects/Keywords: Natural Language Processing; Robotics; ROS

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Kakusa, T. L. (2018). Use of Assembly Inspired Instructions in the Allowance of Natural Language Processing in ROS. (Masters Thesis). Virginia Tech. Retrieved from http://hdl.handle.net/10919/84521

Chicago Manual of Style (16^th Edition):

Kakusa, Takondwa Lisungu. “Use of Assembly Inspired Instructions in the Allowance of Natural Language Processing in ROS.” 2018. Masters Thesis, Virginia Tech. Accessed February 22, 2020. http://hdl.handle.net/10919/84521.

MLA Handbook (7^th Edition):

Kakusa, Takondwa Lisungu. “Use of Assembly Inspired Instructions in the Allowance of Natural Language Processing in ROS.” 2018. Web. 22 Feb 2020.

Vancouver:

Kakusa TL. Use of Assembly Inspired Instructions in the Allowance of Natural Language Processing in ROS. [Internet] [Masters thesis]. Virginia Tech; 2018. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/10919/84521.

Council of Science Editors:

Kakusa TL. Use of Assembly Inspired Instructions in the Allowance of Natural Language Processing in ROS. [Masters Thesis]. Virginia Tech; 2018. Available from: http://hdl.handle.net/10919/84521

University of Houston

11. Kulkarni, Akshay Bhavani Kumar 1994-. Early Detection of Depression.

Degree: Computer Science, Department of, 2018, University of Houston

URL: http://hdl.handle.net/10657/3089

► Depression is a mental disorder that affects more than 300 million people worldwide. An individual suffering from depression functions poorly in life, is prone to… (more)

▼ Depression is a mental disorder that affects more than 300 million people worldwide. An individual suffering from depression functions poorly in life, is prone to other diseases and in the worst-case, depression leads to suicide. There are many impediments that prevent expert care from reaching people suffering from depression in time. Impediments such as social stigma associated with mental disorders, lack of trained health-care professionals and ignorance of the signs of depression owing to a lack of awareness of the disease. Moreover, the World Health Organization (WHO) claims that individuals who are depressed are often not correctly diagnosed and others who are misdiagnosed are prescribed antidepressants. Thus, there is a strong need to automatically assess the risk of depression. Identification of depression from social media has been framed as a classification problem in the field of Natural Language Processing (NLP). In this work we study NLP approaches that can successfully extract information from textual data to enhance identification of depression. These NLP approaches perform feature extraction to build document representations. The issues of detecting depression in a social media environment is data scarcity for users with depression and the inherent noise associated with social media data. We attempt to address those issues by using representations that can naturally cope with a social media environment. Specifically, we propose the usage of Distributed Term Representations (DTRs) to capture information that can be used by supervised machine learning methods for learning and classifying users suffering from depression. Experimental evaluation provides evidence that DTRs are more effective for depression detection than traditional representations such as Bag of Words (BOW) and representations based on neural word embeddings. In fact, we have obtained state-of-the-art results with Document Occurrence Representation (DOR) for depression detection (F1-Score 0.66 on the depressed class). For early detection of depression, we have obtained the lowest reported Early Risk Detection Error (ERDE) using Pyramidal a newly adapted method that is used for computing document representations. Advisors/Committee Members: Solorio, Thamar (advisor), Gonzalez, Fabio A. (committee member), Eick, Christoph F. (committee member).

Subjects/Keywords: Natural Language Processing; Health Care

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Kulkarni, A. B. K. 1. (2018). Early Detection of Depression. (Thesis). University of Houston. Retrieved from http://hdl.handle.net/10657/3089

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Kulkarni, Akshay Bhavani Kumar 1994-. “Early Detection of Depression.” 2018. Thesis, University of Houston. Accessed February 22, 2020. http://hdl.handle.net/10657/3089.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Kulkarni, Akshay Bhavani Kumar 1994-. “Early Detection of Depression.” 2018. Web. 22 Feb 2020.

Vancouver:

Kulkarni ABK1. Early Detection of Depression. [Internet] [Thesis]. University of Houston; 2018. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/10657/3089.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Kulkarni ABK1. Early Detection of Depression. [Thesis]. University of Houston; 2018. Available from: http://hdl.handle.net/10657/3089

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Vanderbilt University

12. Davis, Mary Feller. Determining the Use of Electronic Medical Records in Genetic Studies of Multiple Sclerosis.

Degree: PhD, Human Genetics, 2013, Vanderbilt University

URL: http://etd.library.vanderbilt.edu/available/etd-11302013-193738/ ;

► The clinical course of multiple sclerosis (MS) is highly variable, and research data collection is costly and time-consuming. Much is known about the genetic risk… (more)

Subjects/Keywords: genetic association; natural language processing

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Davis, M. F. (2013). Determining the Use of Electronic Medical Records in Genetic Studies of Multiple Sclerosis. (Doctoral Dissertation). Vanderbilt University. Retrieved from http://etd.library.vanderbilt.edu/available/etd-11302013-193738/ ;

Chicago Manual of Style (16^th Edition):

Davis, Mary Feller. “Determining the Use of Electronic Medical Records in Genetic Studies of Multiple Sclerosis.” 2013. Doctoral Dissertation, Vanderbilt University. Accessed February 22, 2020. http://etd.library.vanderbilt.edu/available/etd-11302013-193738/ ;.

MLA Handbook (7^th Edition):

Davis, Mary Feller. “Determining the Use of Electronic Medical Records in Genetic Studies of Multiple Sclerosis.” 2013. Web. 22 Feb 2020.

Vancouver:

Davis MF. Determining the Use of Electronic Medical Records in Genetic Studies of Multiple Sclerosis. [Internet] [Doctoral dissertation]. Vanderbilt University; 2013. [cited 2020 Feb 22]. Available from: http://etd.library.vanderbilt.edu/available/etd-11302013-193738/ ;.

Council of Science Editors:

Davis MF. Determining the Use of Electronic Medical Records in Genetic Studies of Multiple Sclerosis. [Doctoral Dissertation]. Vanderbilt University; 2013. Available from: http://etd.library.vanderbilt.edu/available/etd-11302013-193738/ ;

University of Guelph

13. Stantic, Daniel. A Unified Probabilistic Model for Aspect-Level Sentiment Analysis .

Degree: 2016, University of Guelph

URL: https://atrium.lib.uoguelph.ca/xmlui/handle/10214/9616

► In this thesis, we develop a new probabilistic model for aspect-level sentiment analysis based on POSLDA, a topic classifier that incorporates syntax modelling for better… (more)

Subjects/Keywords: natural language processing; sentiment analysis

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Stantic, D. (2016). A Unified Probabilistic Model for Aspect-Level Sentiment Analysis . (Thesis). University of Guelph. Retrieved from https://atrium.lib.uoguelph.ca/xmlui/handle/10214/9616

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Stantic, Daniel. “A Unified Probabilistic Model for Aspect-Level Sentiment Analysis .” 2016. Thesis, University of Guelph. Accessed February 22, 2020. https://atrium.lib.uoguelph.ca/xmlui/handle/10214/9616.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Stantic, Daniel. “A Unified Probabilistic Model for Aspect-Level Sentiment Analysis .” 2016. Web. 22 Feb 2020.

Vancouver:

Stantic D. A Unified Probabilistic Model for Aspect-Level Sentiment Analysis . [Internet] [Thesis]. University of Guelph; 2016. [cited 2020 Feb 22]. Available from: https://atrium.lib.uoguelph.ca/xmlui/handle/10214/9616.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Stantic D. A Unified Probabilistic Model for Aspect-Level Sentiment Analysis . [Thesis]. University of Guelph; 2016. Available from: https://atrium.lib.uoguelph.ca/xmlui/handle/10214/9616

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Texas – Austin

14. -7062-2970. Advances in statistical script learning.

Degree: PhD, Computer Science, 2017, University of Texas – Austin

URL: http://hdl.handle.net/2152/63480

► When humans encode information into natural language, they do so with the clear assumption that the reader will be able to seamlessly make inferences based… (more)

▼ When humans encode information into natural language, they do so with the clear assumption that the reader will be able to seamlessly make inferences based on world knowledge. For example, given the sentence ``Mrs. Dalloway said she would buy the flowers herself,'' one can make a number of probable inferences based on event co-occurrences: she bought flowers, she went to a store, she took the flowers home, and so on. Observing this, it is clear that many different useful natural language end-tasks could benefit from models of events as they typically co-occur (so-called script models). Robust question-answering systems must be able to infer highly-probable implicit events from what is explicitly stated in a text, as must robust information-extraction systems that map from unstructured text to formal assertions about relations expressed in the text. Coreference resolution systems, semantic role labeling, and even syntactic parsing systems could, in principle, benefit from event co-occurrence models. To this end, we present a number of contributions related to statistical event co-occurrence models. First, we investigate a method of incorporating multiple entities into events in a count-based co-occurrence model. We find that modeling multiple entities interacting across events allows for improved empirical performance on the task of modeling sequences of events in documents. Second, we give a method of applying Recurrent Neural Network sequence models to the task of predicting held-out predicate-argument structures from documents. This model allows us to easily incorporate entity noun information, and can allow for more complex, higher-arity events than a count-based co-occurrence model. We find the neural model improves performance considerably over the count-based co-occurrence model. Third, we investigate the performance of a sequence-to-sequence encoder-decoder neural model on the task of predicting held-out predicate-argument events from text. This model does not explicitly model any external syntactic information, and does not require a parser. We find the text-level model to be competitive in predictive performance with an event level model directly mediated by an external syntactic analysis. Finally, motivated by this result, we investigate incorporating features derived from these models into a baseline noun coreference resolution system. We find that, while our additional features do not appreciably improve top-level performance, we can nonetheless provide empirical improvement on a number of restricted classes of difficult coreference decisions. Advisors/Committee Members: Mooney, Raymond J. (Raymond Joseph) (advisor), Chambers, Nathanael (committee member), Erk, Katrin (committee member), Stone, Peter (committee member).

Subjects/Keywords: Natural language processing; Machine learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

-7062-2970. (2017). Advances in statistical script learning. (Doctoral Dissertation). University of Texas – Austin. Retrieved from http://hdl.handle.net/2152/63480

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Chicago Manual of Style (16^th Edition):

-7062-2970. “Advances in statistical script learning.” 2017. Doctoral Dissertation, University of Texas – Austin. Accessed February 22, 2020. http://hdl.handle.net/2152/63480.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

MLA Handbook (7^th Edition):

-7062-2970. “Advances in statistical script learning.” 2017. Web. 22 Feb 2020.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Vancouver:

-7062-2970. Advances in statistical script learning. [Internet] [Doctoral dissertation]. University of Texas – Austin; 2017. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/2152/63480.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Council of Science Editors:

-7062-2970. Advances in statistical script learning. [Doctoral Dissertation]. University of Texas – Austin; 2017. Available from: http://hdl.handle.net/2152/63480

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

University of Sydney

15. Pink, Glen Alan. Slot Filling .

Degree: 2017, University of Sydney

URL: http://hdl.handle.net/2123/17055

► Slot filling (SF) is the task of automatically extracting facts about particular entities from unstructured text, and populating a knowledge base (KB) with these facts.… (more)

▼ Slot filling (SF) is the task of automatically extracting facts about particular entities from unstructured text, and populating a knowledge base (KB) with these facts. These structured KBs enable applications such as structured web queries and question answering. SF is typically framed as a query-oriented setting of the related task of relation extraction. Throughout this thesis, we reflect on how SF is a task with many distinct problems. We demonstrate that recall is a major limiter on SF system performance. We contribute an analysis of typical SF recall loss, and find a substantial amount of loss occurs early in the SF pipeline. We confirm that accurate NER and coreference resolution are required for high-recall SF. We measure upper bounds using a naïve graph-based semi-supervised bootstrapping technique, and find that only 39% of results are reachable using a typical feature space. We expect that this graph-based technique will be directly useful for extraction, and this leads us to frame SF as a label propagation task. We focus on a detailed graph representation of the task which reflects the behaviour and assumptions we want to model based on our analysis, including modifying the label propagation process to model multiple types of label interaction. Analysing the graph, we find that a large number of errors occur in very close proximity to training data, and identify that this is of major concern for propagation. While there are some conflicts caused by a lack of sufficient disambiguating context—we explore adding additional contextual features to address this—many of these conflicts are caused by subtle annotation problems. We find that lack of a standard for how explicit expressions of relations must be in text makes consistent annotation difficult. Using a strict definition of explicitness results in 20% of correct annotations being removed from a standard dataset. We contribute several annotation-driven analyses of this problem, exploring the definition of slots and the effect of the lack of a concrete definition of explicitness: annotation schema do not detail how explicit expressions of relations need to be, and there is large scope for disagreement between annotators. Additionally, applications may require relatively strict or relaxed evidence for extractions, but this is not considered in annotation tasks. We demonstrate that annotators frequently disagree on instances, dependent on differences in annotator world knowledge and thresholds on making probabilistic inference. SF is fundamental to enabling many knowledge-based applications, and this work motivates modelling and evaluating SF to better target these tasks.

Subjects/Keywords: natural language processing; information; extraction

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Pink, G. A. (2017). Slot Filling . (Thesis). University of Sydney. Retrieved from http://hdl.handle.net/2123/17055

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Pink, Glen Alan. “Slot Filling .” 2017. Thesis, University of Sydney. Accessed February 22, 2020. http://hdl.handle.net/2123/17055.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Pink, Glen Alan. “Slot Filling .” 2017. Web. 22 Feb 2020.

Vancouver:

Pink GA. Slot Filling . [Internet] [Thesis]. University of Sydney; 2017. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/2123/17055.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Pink GA. Slot Filling . [Thesis]. University of Sydney; 2017. Available from: http://hdl.handle.net/2123/17055

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Virginia Tech

16. Patil, Supritha Basavaraj. Analysis of Moving Events Using Tweets.

Degree: MS, Computer Science and Applications, 2019, Virginia Tech

URL: http://hdl.handle.net/10919/90884

► News now travels faster on social media than through news channels. Information from social media can help retrieve minute details that might not be emphasized… (more)

Subjects/Keywords: Natural Language Processing; Twitter

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Patil, S. B. (2019). Analysis of Moving Events Using Tweets. (Masters Thesis). Virginia Tech. Retrieved from http://hdl.handle.net/10919/90884

Chicago Manual of Style (16^th Edition):

Patil, Supritha Basavaraj. “Analysis of Moving Events Using Tweets.” 2019. Masters Thesis, Virginia Tech. Accessed February 22, 2020. http://hdl.handle.net/10919/90884.

MLA Handbook (7^th Edition):

Patil, Supritha Basavaraj. “Analysis of Moving Events Using Tweets.” 2019. Web. 22 Feb 2020.

Vancouver:

Patil SB. Analysis of Moving Events Using Tweets. [Internet] [Masters thesis]. Virginia Tech; 2019. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/10919/90884.

Council of Science Editors:

Patil SB. Analysis of Moving Events Using Tweets. [Masters Thesis]. Virginia Tech; 2019. Available from: http://hdl.handle.net/10919/90884

McMaster University

17. Cui, Yexin. Language Identification on Short Textual Data.

Degree: MASc, 2020, McMaster University

URL: http://hdl.handle.net/11375/25126

►

Language identification is the task of automatically detecting the languages(s) written in a text or a document given, and is also the very first step… (more)

Subjects/Keywords: Natural Language Processing; Language identification; Textual data

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Cui, Y. (2020). Language Identification on Short Textual Data. (Masters Thesis). McMaster University. Retrieved from http://hdl.handle.net/11375/25126

Chicago Manual of Style (16^th Edition):

Cui, Yexin. “Language Identification on Short Textual Data.” 2020. Masters Thesis, McMaster University. Accessed February 22, 2020. http://hdl.handle.net/11375/25126.

MLA Handbook (7^th Edition):

Cui, Yexin. “Language Identification on Short Textual Data.” 2020. Web. 22 Feb 2020.

Vancouver:

Cui Y. Language Identification on Short Textual Data. [Internet] [Masters thesis]. McMaster University; 2020. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/11375/25126.

Council of Science Editors:

Cui Y. Language Identification on Short Textual Data. [Masters Thesis]. McMaster University; 2020. Available from: http://hdl.handle.net/11375/25126

University of Edinburgh

18. Brockmann, Carsten. Personality and alignment processes in dialogue : towards a lexically-based unified model.

Degree: PhD, 2009, University of Edinburgh

URL: http://hdl.handle.net/1842/3980

► This thesis explores approaches to modelling individual differences in language use. The differences under consideration fall into two broad categories: Variation of the personality projected… (more)

▼ This thesis explores approaches to modelling individual differences in language use. The differences under consideration fall into two broad categories: Variation of the personality projected through language, and modelling of language alignment behaviour between dialogue partners. In a way, these two aspects oppose each other – language related to varying personalities should be recognisably different, while aligning speakers agree on common language during a dialogue. The central hypothesis is that such variation can be captured and produced with restricted computational means. Results from research on personality psychology and psycholinguistics are transformed into a series of lexically-based Affective Language Production Models (ALPMs) which are parameterisable for personality and alignment. The models are then explored by varying the parameters and observing the language they generate. ALPM-1 and ALPM-2 re-generate dialogues from existing utterances which are ranked and filtered according to manually selected linguistic and psycholinguistic features that were found to be related to personality. ALPM-3 is based on true overgeneration of paraphrases from semantic representations using the OPENCCG framework for Combinatory Categorial Grammar (CCG), in combination with corpus-based ranking and filtering by way of n-gram language models. Personality effects are achieved through language models built from the language of speakers of known personality. In ALPM-4, alignment is captured via a cache language model that remembers the previous utterance and thus influences the choice of the next. This model provides a unified treatment of personality and alignment processes in dialogue. In order to evaluate the ALPMs, dialogues between computer characters were generated and presented to human judges who were asked to assess the characters’ personality. In further internal simulations, cache language models were used to reproduce results of psycholinguistic priming studies. The experiments showed that the models are capable of producing natural language dialogue which exhibits human-like personality and alignment effects.

Subjects/Keywords: 410; personality; alignment; dialogue; natural language processing; natural language generation

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Brockmann, C. (2009). Personality and alignment processes in dialogue : towards a lexically-based unified model. (Doctoral Dissertation). University of Edinburgh. Retrieved from http://hdl.handle.net/1842/3980

Chicago Manual of Style (16^th Edition):

Brockmann, Carsten. “Personality and alignment processes in dialogue : towards a lexically-based unified model.” 2009. Doctoral Dissertation, University of Edinburgh. Accessed February 22, 2020. http://hdl.handle.net/1842/3980.

MLA Handbook (7^th Edition):

Brockmann, Carsten. “Personality and alignment processes in dialogue : towards a lexically-based unified model.” 2009. Web. 22 Feb 2020.

Vancouver:

Brockmann C. Personality and alignment processes in dialogue : towards a lexically-based unified model. [Internet] [Doctoral dissertation]. University of Edinburgh; 2009. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/1842/3980.

Council of Science Editors:

Brockmann C. Personality and alignment processes in dialogue : towards a lexically-based unified model. [Doctoral Dissertation]. University of Edinburgh; 2009. Available from: http://hdl.handle.net/1842/3980

19. Dong, Li. Learning natural language interfaces with neural models.

Degree: PhD, 2019, University of Edinburgh

URL: http://hdl.handle.net/1842/35587

► Language is the primary and most natural means of communication for humans. The learning curve of interacting with various devices and services (e.g., digital assistants,… (more)

▼ Language is the primary and most natural means of communication for humans. The learning curve of interacting with various devices and services (e.g., digital assistants, and smart appliances) would be greatly reduced if we could talk to machines using human language. However, in most cases computers can only interpret and execute formal languages. In this thesis, we focus on using neural models to build natural language interfaces which learn to map naturally worded expressions onto machineinterpretable representations. The task is challenging due to (1) structural mismatches between natural language and formal language, (2) the well-formedness of output representations, (3) lack of uncertainty information and interpretability, and (4) the model coverage for language variations. In this thesis, we develop several flexible neural architectures to address these challenges. We propose a model based on attention-enhanced encoder-decoder neural networks for natural language interfaces. Beyond sequence modeling, we propose a tree decoder to utilize the compositional nature and well-formedness of meaning representations, which recursively generates hierarchical structures in a top-down manner. To model meaning at different levels of granularity, we present a structure-aware neural architecture which decodes semantic representations following a coarse-to-fine procedure. The proposed neural models remain difficult to interpret, acting in most cases as a black box. We explore ways to estimate and interpret the model's confidence in its predictions, which we argue can provide users with immediate and meaningful feedback regarding uncertain outputs. We estimate confidence scores that indicate whether model predictions are likely to be correct. Moreover, we identify which parts of the input contribute to uncertain predictions allowing users to interpret their model. Model coverage is one of the major reasons resulting in uncertainty of natural language interfaces. Therefore, we develop a general framework to handle the many different ways natural language expresses the same information need. We leverage external resources to generate felicitous paraphrases for the input, and then feed them to a neural paraphrase scoring model which assigns higher weights to linguistic expressions most likely to yield correct answers. The model components are trained end-to-end using supervision signals provided by the target task. Experimental results show that the proposed neural models can be easily ported across tasks. Moreover, the robustness of natural language interfaces can be enhanced by considering the output well-formedness, confidence modeling, and improving model coverage.

Subjects/Keywords: natural language interface; question answering; natural language processing

7 more images…

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Dong, L. (2019). Learning natural language interfaces with neural models. (Doctoral Dissertation). University of Edinburgh. Retrieved from http://hdl.handle.net/1842/35587

Chicago Manual of Style (16^th Edition):

Dong, Li. “Learning natural language interfaces with neural models.” 2019. Doctoral Dissertation, University of Edinburgh. Accessed February 22, 2020. http://hdl.handle.net/1842/35587.

MLA Handbook (7^th Edition):

Dong, Li. “Learning natural language interfaces with neural models.” 2019. Web. 22 Feb 2020.

Vancouver:

Dong L. Learning natural language interfaces with neural models. [Internet] [Doctoral dissertation]. University of Edinburgh; 2019. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/1842/35587.

Council of Science Editors:

Dong L. Learning natural language interfaces with neural models. [Doctoral Dissertation]. University of Edinburgh; 2019. Available from: http://hdl.handle.net/1842/35587

University of Rochester

20. Naim, Iftekhar. Unsupervised alignment of natural language with video.

Degree: PhD, 2016, University of Rochester

URL: http://hdl.handle.net/1802/30614

► Today we encounter large amounts of video data, often accompanied with text descriptions (e.g., cooking videos and recipes, videos of wetlab experiments and protocols, movies… (more)

Subjects/Keywords: Alignment; Computer vision; Language and vision; Natural language processing; Video processing

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Naim, I. (2016). Unsupervised alignment of natural language with video. (Doctoral Dissertation). University of Rochester. Retrieved from http://hdl.handle.net/1802/30614

Chicago Manual of Style (16^th Edition):

Naim, Iftekhar. “Unsupervised alignment of natural language with video.” 2016. Doctoral Dissertation, University of Rochester. Accessed February 22, 2020. http://hdl.handle.net/1802/30614.

MLA Handbook (7^th Edition):

Naim, Iftekhar. “Unsupervised alignment of natural language with video.” 2016. Web. 22 Feb 2020.

Vancouver:

Naim I. Unsupervised alignment of natural language with video. [Internet] [Doctoral dissertation]. University of Rochester; 2016. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/1802/30614.

Council of Science Editors:

Naim I. Unsupervised alignment of natural language with video. [Doctoral Dissertation]. University of Rochester; 2016. Available from: http://hdl.handle.net/1802/30614

Universitat Politècnica de València

21. Reyes Pérez, Antonio. Linguistic-based Patterns for Figurative Language Processing: The Case of Humor Recognition and Irony Detection .

Degree: 2012, Universitat Politècnica de València

URL: http://hdl.handle.net/10251/16692

► El lenguaje figurado representa una de las tareas más difíciles del procesamiento del lenguaje natural. A diferencia del lenguaje literal, el lenguaje figurado hace uso… (more)

▼ El lenguaje figurado representa una de las tareas más difíciles del procesamiento del lenguaje natural. A diferencia del lenguaje literal, el lenguaje figurado hace uso de recursos lingüísticos tales como la ironía, el humor, el sarcasmo, la metáfora, la analogía, entre otros, para comunicar significados indirectos que la mayoría de las veces no son interpretables sólo en términos de información sintáctica o semántica. Por el contrario, el lenguaje figurado refleja patrones del pensamiento que adquieren significado pleno en contextos comunicativos y sociales, lo cual hace que tanto su representación lingüística, así como su procesamiento computacional, se vuelvan tareas por demás complejas. En este contexto, en esta tesis de doctorado se aborda una problemática relacionada con el procesamiento del lenguaje figurado a partir de patrones lingüísticos. En particular, nuestros esfuerzos se centran en la creación de un sistema capaz de detectar automáticamente instancias de humor e ironía en textos extraídos de medios sociales. Nuestra hipótesis principal se basa en la premisa de que el lenguaje refleja patrones de conceptualización; es decir, al estudiar el lenguaje, estudiamos tales patrones. Por tanto, al analizar estos dos dominios del lenguaje figurado, pretendemos dar argumentos respecto a cómo la gente los concibe, y sobre todo, a cómo esa concepción hace que tanto humor como ironía sean verbalizados de una forma particular en diversos medios sociales. En este contexto, uno de nuestros mayores intereses es demostrar cómo el conocimiento que proviene del análisis de diferentes niveles de estudio lingüístico puede representar un conjunto de patrones relevantes para identificar automáticamente usos figurados del lenguaje. Cabe destacar que contrario a la mayoría de aproximaciones que se han enfocado en el estudio del lenguaje figurado, en nuestra investigación no buscamos dar argumentos basados únicamente en ejemplos prototípicos, sino en textos cuyas características Advisors/Committee Members: Rosso ., Paolo (advisor).

Subjects/Keywords: Automatic humor recognition; Irony detection; Figurative language processing; Natural language processing

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Reyes Pérez, A. (2012). Linguistic-based Patterns for Figurative Language Processing: The Case of Humor Recognition and Irony Detection . (Doctoral Dissertation). Universitat Politècnica de València. Retrieved from http://hdl.handle.net/10251/16692

Chicago Manual of Style (16^th Edition):

Reyes Pérez, Antonio. “Linguistic-based Patterns for Figurative Language Processing: The Case of Humor Recognition and Irony Detection .” 2012. Doctoral Dissertation, Universitat Politècnica de València. Accessed February 22, 2020. http://hdl.handle.net/10251/16692.

MLA Handbook (7^th Edition):

Reyes Pérez, Antonio. “Linguistic-based Patterns for Figurative Language Processing: The Case of Humor Recognition and Irony Detection .” 2012. Web. 22 Feb 2020.

Vancouver:

Reyes Pérez A. Linguistic-based Patterns for Figurative Language Processing: The Case of Humor Recognition and Irony Detection . [Internet] [Doctoral dissertation]. Universitat Politècnica de València; 2012. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/10251/16692.

Council of Science Editors:

Reyes Pérez A. Linguistic-based Patterns for Figurative Language Processing: The Case of Humor Recognition and Irony Detection . [Doctoral Dissertation]. Universitat Politècnica de València; 2012. Available from: http://hdl.handle.net/10251/16692

Hong Kong University of Science and Technology

22. Yu, Jinxing CSE. Joint embeddings of Chinese words, characters, and fine-grained subcharacter components.

Degree: 2017, Hong Kong University of Science and Technology

URL: http://repository.ust.hk/ir/Record/1783.1-93101 ; https://doi.org/10.14711/thesis-991012572162503412 ; http://repository.ust.hk/ir/bitstream/1783.1-93101/1/th_redirect.html

► Word embeddings have attracted much attention recently given their simplicity of word representation and generalization ability for a lot of downstream tasks. Different from alphabetic… (more)

Subjects/Keywords: Natural language processing (Computer science) ; Chinese language ; Data processing ; Computational linguistics

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Yu, J. C. (2017). Joint embeddings of Chinese words, characters, and fine-grained subcharacter components. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-93101 ; https://doi.org/10.14711/thesis-991012572162503412 ; http://repository.ust.hk/ir/bitstream/1783.1-93101/1/th_redirect.html

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Yu, Jinxing CSE. “Joint embeddings of Chinese words, characters, and fine-grained subcharacter components.” 2017. Thesis, Hong Kong University of Science and Technology. Accessed February 22, 2020. http://repository.ust.hk/ir/Record/1783.1-93101 ; https://doi.org/10.14711/thesis-991012572162503412 ; http://repository.ust.hk/ir/bitstream/1783.1-93101/1/th_redirect.html.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Yu, Jinxing CSE. “Joint embeddings of Chinese words, characters, and fine-grained subcharacter components.” 2017. Web. 22 Feb 2020.

Vancouver:

Yu JC. Joint embeddings of Chinese words, characters, and fine-grained subcharacter components. [Internet] [Thesis]. Hong Kong University of Science and Technology; 2017. [cited 2020 Feb 22]. Available from: http://repository.ust.hk/ir/Record/1783.1-93101 ; https://doi.org/10.14711/thesis-991012572162503412 ; http://repository.ust.hk/ir/bitstream/1783.1-93101/1/th_redirect.html.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Yu JC. Joint embeddings of Chinese words, characters, and fine-grained subcharacter components. [Thesis]. Hong Kong University of Science and Technology; 2017. Available from: http://repository.ust.hk/ir/Record/1783.1-93101 ; https://doi.org/10.14711/thesis-991012572162503412 ; http://repository.ust.hk/ir/bitstream/1783.1-93101/1/th_redirect.html

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Reykjavík University

23. Svavar Kjarrval Lúthersson. Tagging and parsing a large corpus.

Degree: 2010, Reykjavík University

URL: http://hdl.handle.net/1946/9883

►

This report is a product of a research where we tried to use existing language processing tools on a larger collection of Icelandic sentences than… (more)

Subjects/Keywords: Máltækni; Natural language processing (Computer science)

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Lúthersson, S. K. (2010). Tagging and parsing a large corpus. (Thesis). Reykjavík University. Retrieved from http://hdl.handle.net/1946/9883

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Lúthersson, Svavar Kjarrval. “Tagging and parsing a large corpus.” 2010. Thesis, Reykjavík University. Accessed February 22, 2020. http://hdl.handle.net/1946/9883.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Lúthersson, Svavar Kjarrval. “Tagging and parsing a large corpus.” 2010. Web. 22 Feb 2020.

Vancouver:

Lúthersson SK. Tagging and parsing a large corpus. [Internet] [Thesis]. Reykjavík University; 2010. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/1946/9883.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Lúthersson SK. Tagging and parsing a large corpus. [Thesis]. Reykjavík University; 2010. Available from: http://hdl.handle.net/1946/9883

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Texas A&M University

24. Zhang, Weiwei. Search Text Based on Locations.

Degree: 2014, Texas A&M University

URL: http://hdl.handle.net/1969.1/153809

► To satisfy the current need for finding queried information quickly, search engines, data mining systems, and many other applications have been in development in recent… (more)

▼ To satisfy the current need for finding queried information quickly, search engines, data mining systems, and many other applications have been in development in recent years. Some of those applications look for documents containing phrases of a particular topic, such as historical events from a certain time period. Among these applications, queries based on geographical data are receiving significant attention from the research community and industry. Therefore, this thesis studies text search based locations, which contributes to the Geographical Information Retrieval (GIR) systems. In addition to the traditional applications of GIR systems, which are used for finding locations in documents, GIR can be applied to other fields as well. Firstly, it can retrieve location information in text and search for answers to questions of a spatial nature (such as \Where is College Station?"). Location information can improve presentation of the search results, for example, by presenting the search results on a map. GIR also adds to the field of spatial diversity search, which allows users to express preferences and constrain the search results to a particular geographical region. In addition, it finds related document based on location information from different sources of information and then represents the similarities graphically. In this way, the readers can visually see the data, helping them understand the document correlations in an intuitive way. However, most of the previous research involves keyword searches in spatial databases instead of raw (unlabeled) text. Although there is some work on raw text processing, that work uses matching techniques, and limits the geographical range to small geographical regions such as a single country. Therefore, this thesis adopts a new clustering method, which utilizes a geographical dictionary to locate any place by its coordinates. This method reduces ambiguity and improves the accuracy over the previous research. This study also implements a new word-clustering method to detect a combination of topics in raw text. This method is more accurate than the latent Dirichlet allocation, a state of the art method based on a probabilistic model. In addition, a novel graphic illustration is utilized to visually represent the relevance ranking between documents. Advisors/Committee Members: Sprintson, Alexander (advisor), Jiang, Anxiao (advisor), Shakkottai, Srinivas (committee member).

Subjects/Keywords: Geographical information retrieval; natural language processing

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Zhang, W. (2014). Search Text Based on Locations. (Thesis). Texas A&M University. Retrieved from http://hdl.handle.net/1969.1/153809

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Zhang, Weiwei. “Search Text Based on Locations.” 2014. Thesis, Texas A&M University. Accessed February 22, 2020. http://hdl.handle.net/1969.1/153809.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Zhang, Weiwei. “Search Text Based on Locations.” 2014. Web. 22 Feb 2020.

Vancouver:

Zhang W. Search Text Based on Locations. [Internet] [Thesis]. Texas A&M University; 2014. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/1969.1/153809.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Zhang W. Search Text Based on Locations. [Thesis]. Texas A&M University; 2014. Available from: http://hdl.handle.net/1969.1/153809

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Aberdeen

25. Mitchell, Margaret. Generating reference to visible objects.

Degree: PhD, 2013, University of Aberdeen

URL: http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=201692 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.577669

► In this thesis, I examine human-like language generation from a visual input head-on, exploring how people refer to visible objects in the real world. Using… (more)

Subjects/Keywords: 004; Natural language processing (Computer science)

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Mitchell, M. (2013). Generating reference to visible objects. (Doctoral Dissertation). University of Aberdeen. Retrieved from http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=201692 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.577669

Chicago Manual of Style (16^th Edition):

Mitchell, Margaret. “Generating reference to visible objects.” 2013. Doctoral Dissertation, University of Aberdeen. Accessed February 22, 2020. http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=201692 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.577669.

MLA Handbook (7^th Edition):

Mitchell, Margaret. “Generating reference to visible objects.” 2013. Web. 22 Feb 2020.

Vancouver:

Mitchell M. Generating reference to visible objects. [Internet] [Doctoral dissertation]. University of Aberdeen; 2013. [cited 2020 Feb 22]. Available from: http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=201692 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.577669.

Council of Science Editors:

Mitchell M. Generating reference to visible objects. [Doctoral Dissertation]. University of Aberdeen; 2013. Available from: http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=201692 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.577669

University of Aberdeen

26. Venour, Chris. A computational model of lexical incongruity in humorous text.

Degree: PhD, 2013, University of Aberdeen

URL: http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=201735 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.577671

► Many theories of humour claim that incongruity is an essential ingredient of humour. How- ever this idea is poorly understood and little work has been… (more)

▼ Many theories of humour claim that incongruity is an essential ingredient of humour. How- ever this idea is poorly understood and little work has been done in computational humour to quantify it. For example classifiers which attempt to distinguish jokes from regular texts tend to look for secondary features of humorous texts rather than for incongruity. Similarly most joke generators attempt to recreate structural patterns found in example jokes but do not deliberately endeavour to create incongruity. As in previous research, this thesis develops classifiers and a joke generator which attempt to automatically recognize and generate a type of humour. However the systems described here differ from previous programs because they implement a model of a certain type of humorous incongruity. We focus on a type of register humour we call lexical register jokes in which the tones of individual words are in conflict with each other. Our goal is to create a semantic space that reflects the kind of tone at play in lexical register jokes so that words that are far apart in the space are not simply different but exhibit the kinds of incongruities seen in lexical jokes. This thesis attempts to develop such a space and various classifiers are implemented to use it to distinguish lexical register jokes from regular texts. The best of these classifiers achieved high levels of accuracy when distinguishing between a test set of lexical register jokes and 4 different kinds of regular text. A joke generator which makes use of the semantic space to create original lexical register jokes is also implemented and described in this thesis. In a test of the generator, texts that were generated by the system were evaluated by volunteers who considered them not as humorous as human-made lexical register jokes but significantly more humorous than a set of control (i.e.non- joke) texts. This was an encouraging result which suggests that the vector space is somewhat successful in discovering lexical differences in tone and in modelling lexical register jokes.

Subjects/Keywords: 004; Natural language processing (Computer science)

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Venour, C. (2013). A computational model of lexical incongruity in humorous text. (Doctoral Dissertation). University of Aberdeen. Retrieved from http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=201735 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.577671

Chicago Manual of Style (16^th Edition):

Venour, Chris. “A computational model of lexical incongruity in humorous text.” 2013. Doctoral Dissertation, University of Aberdeen. Accessed February 22, 2020. http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=201735 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.577671.

MLA Handbook (7^th Edition):

Venour, Chris. “A computational model of lexical incongruity in humorous text.” 2013. Web. 22 Feb 2020.

Vancouver:

Venour C. A computational model of lexical incongruity in humorous text. [Internet] [Doctoral dissertation]. University of Aberdeen; 2013. [cited 2020 Feb 22]. Available from: http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=201735 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.577671.

Council of Science Editors:

Venour C. A computational model of lexical incongruity in humorous text. [Doctoral Dissertation]. University of Aberdeen; 2013. Available from: http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=201735 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.577671

Oregon State University

27. Arbogast, Christian. Assessing Student Conceptual Understanding : Supplementing Deductive Coding with Natural Language Processing Techniques.

Degree: MS, Mechanical Engineering, 2016, Oregon State University

URL: http://hdl.handle.net/1957/58551

► Assessing student conceptual understanding is a valuable method for gauging specific student learning outcomes but can be difficult and time consuming to measure. This research… (more)

Subjects/Keywords: Conceptual Understanding; Natural language processing (Computer science)

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Arbogast, C. (2016). Assessing Student Conceptual Understanding : Supplementing Deductive Coding with Natural Language Processing Techniques. (Masters Thesis). Oregon State University. Retrieved from http://hdl.handle.net/1957/58551

Chicago Manual of Style (16^th Edition):

Arbogast, Christian. “Assessing Student Conceptual Understanding : Supplementing Deductive Coding with Natural Language Processing Techniques.” 2016. Masters Thesis, Oregon State University. Accessed February 22, 2020. http://hdl.handle.net/1957/58551.

MLA Handbook (7^th Edition):

Arbogast, Christian. “Assessing Student Conceptual Understanding : Supplementing Deductive Coding with Natural Language Processing Techniques.” 2016. Web. 22 Feb 2020.

Vancouver:

Arbogast C. Assessing Student Conceptual Understanding : Supplementing Deductive Coding with Natural Language Processing Techniques. [Internet] [Masters thesis]. Oregon State University; 2016. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/1957/58551.

Council of Science Editors:

Arbogast C. Assessing Student Conceptual Understanding : Supplementing Deductive Coding with Natural Language Processing Techniques. [Masters Thesis]. Oregon State University; 2016. Available from: http://hdl.handle.net/1957/58551

University of Illinois – Urbana-Champaign

28. Plummer, Bryan A. Grounding natural language phrases in images and video.

Degree: PhD, Computer Science, 2018, University of Illinois – Urbana-Champaign

URL: http://hdl.handle.net/2142/100977

► Grounding language in images has shown it can help improve performance on many image-language tasks. To spur research on this topic, this dissertation introduces a… (more)

Subjects/Keywords: Computer Vision; Natural Language Processing; Phrase Grounding

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Plummer, B. A. (2018). Grounding natural language phrases in images and video. (Doctoral Dissertation). University of Illinois – Urbana-Champaign. Retrieved from http://hdl.handle.net/2142/100977

Chicago Manual of Style (16^th Edition):

Plummer, Bryan A. “Grounding natural language phrases in images and video.” 2018. Doctoral Dissertation, University of Illinois – Urbana-Champaign. Accessed February 22, 2020. http://hdl.handle.net/2142/100977.

MLA Handbook (7^th Edition):

Plummer, Bryan A. “Grounding natural language phrases in images and video.” 2018. Web. 22 Feb 2020.

Vancouver:

Plummer BA. Grounding natural language phrases in images and video. [Internet] [Doctoral dissertation]. University of Illinois – Urbana-Champaign; 2018. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/2142/100977.

Council of Science Editors:

Plummer BA. Grounding natural language phrases in images and video. [Doctoral Dissertation]. University of Illinois – Urbana-Champaign; 2018. Available from: http://hdl.handle.net/2142/100977

University of Illinois – Urbana-Champaign

29. Klementiev, Alexandre A. Learning with Incidental Supervision.

Degree: PhD, 0112, 2010, University of Illinois – Urbana-Champaign

URL: http://hdl.handle.net/2142/14553

► Recent technological advances have facilitated the collection and distribution of a plethora of increasingly diverse and complex data. Supervised learning has been able to provide… (more)

▼ Recent technological advances have facilitated the collection and distribution of a plethora of increasingly diverse and complex data. Supervised learning has been able to provide the toolbox of choice for exploiting it to study and model numerous natural and social phenomena. These learning techniques typically require substantial amounts of training data in order to induce good solutions. However, generating annotation often places a significant burden on human experts, and makes supervised learning methods costly to apply. On the other hand, data itself often provides hints sufficient to induce high quality supervision and utilizing these hints can be substantially less labor intensive than producing explicit annotation. This thesis introduces a framework we call Learning with Incidental Supervision, which formalizes these concepts. In particular, we show that various aspects of the data often contain cues capable of inducing weak supervision signals, which could in turn be aggregated to produce high quality annotation. We examine both the derivation of these signals and aggregation of their predictions in the context of concrete learning tasks, making independent contributions in both cases. We use the task of Named Entity Discovery to demonstrate that inherent properties of unsupervised multilingual data readily available online can be used to derive multiple weak supervision signals capable of inducing named entity annotation in a new language. We show that combining these signals can substantially improve the resulting annotation. Next, we introduce a general unsupervised learning framework for aggregating predictions from multiple weak supervision sources in order to induce high quality annotation. We exploit agreement between the signals to estimate their relative quality and learn an effective aggregation model. The mathematical and algorithmic aggregation framework can in principle be applied to combining arbitrary types of predictions, and has a large number of applications on its own. We instantiate it and demonstrate its effectiveness for combining permutations, top-k lists, and dependency parses. Advisors/Committee Members: Roth, Dan (advisor), Roth, Dan (Committee Chair), Forsyth, David A. (committee member), Pereira, Fernando (committee member), Zhai, ChengXiang (committee member).

Subjects/Keywords: machine learning; natural language processing; prediction aggregation

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Klementiev, A. A. (2010). Learning with Incidental Supervision. (Doctoral Dissertation). University of Illinois – Urbana-Champaign. Retrieved from http://hdl.handle.net/2142/14553

Chicago Manual of Style (16^th Edition):

Klementiev, Alexandre A. “Learning with Incidental Supervision.” 2010. Doctoral Dissertation, University of Illinois – Urbana-Champaign. Accessed February 22, 2020. http://hdl.handle.net/2142/14553.

MLA Handbook (7^th Edition):

Klementiev, Alexandre A. “Learning with Incidental Supervision.” 2010. Web. 22 Feb 2020.

Vancouver:

Klementiev AA. Learning with Incidental Supervision. [Internet] [Doctoral dissertation]. University of Illinois – Urbana-Champaign; 2010. [cited 2020 Feb 22]. Available from: http://hdl.handle.net/2142/14553.

Council of Science Editors:

Klementiev AA. Learning with Incidental Supervision. [Doctoral Dissertation]. University of Illinois – Urbana-Champaign; 2010. Available from: http://hdl.handle.net/2142/14553

Brigham Young University

30. Hodgson, Grant Michael. Suggesting Missing Information in Text Documents.

Degree: MS, 2018, Brigham Young University

URL: https://scholarsarchive.byu.edu/cgi/viewcontent.cgi?article=8296&context=etd

► A key part of contract drafting involves thinking of issues that have not been addressedand adding language that will address the missing issues. To assist… (more)

Subjects/Keywords: Natural language processing; suggesting; missing; text

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Hodgson, G. M. (2018). Suggesting Missing Information in Text Documents. (Masters Thesis). Brigham Young University. Retrieved from https://scholarsarchive.byu.edu/cgi/viewcontent.cgi?article=8296&context=etd

Chicago Manual of Style (16^th Edition):

Hodgson, Grant Michael. “Suggesting Missing Information in Text Documents.” 2018. Masters Thesis, Brigham Young University. Accessed February 22, 2020. https://scholarsarchive.byu.edu/cgi/viewcontent.cgi?article=8296&context=etd.

MLA Handbook (7^th Edition):

Hodgson, Grant Michael. “Suggesting Missing Information in Text Documents.” 2018. Web. 22 Feb 2020.

Vancouver:

Hodgson GM. Suggesting Missing Information in Text Documents. [Internet] [Masters thesis]. Brigham Young University; 2018. [cited 2020 Feb 22]. Available from: https://scholarsarchive.byu.edu/cgi/viewcontent.cgi?article=8296&context=etd.

Council of Science Editors:

Hodgson GM. Suggesting Missing Information in Text Documents. [Masters Thesis]. Brigham Young University; 2018. Available from: https://scholarsarchive.byu.edu/cgi/viewcontent.cgi?article=8296&context=etd

		in
And / Or
		in
And / Or
		in
And / Or
		in

Open Access Theses and Dissertations