peer-reviewed

The evaluation of the quality of a translation is still a time consuming manual operation depending on human intervention. Confidence Estimation (CE) explores the prediction of the quality of a translation from the attributes of a sentence (Blatz et al. 2004; Specia et al. 2009; Specia and Shah 2014). Cognitive translatology searches for a proficient translator from the dispositions of a person (O'Brien 2013; Jääskeläinen 2010; Muñoz Martín 2010a; House 2014). This study explored the prediction of the quality of translation between ‘Good’ and ‘Bad’ from certain attributes of a translator using a J48 decision tree algorithm with 10-fold cross validation on the WEKA machine learning platform. The data preparation for all J48 experiments (source text design, translation evaluation metrics, the selection of attributes, and the selection of candidates) were examined in a pilot study with 22 participants. The main study consisted of 82 participants with three groups of translators: professional translator, casual translator, and student. Each participant was described by the values of 146 attributes from six categories (arts, sports, pastime activities, life style, personality, and background). The evaluation of 25 sentences from two topics by four native English speakers was the basis of their quality scores. Krippendorff’s Alpha (Hayes and Krippendorff 2007) measured 0.7342 for Nugget Recall and 0.6079 for fluency suggesting acceptable agreement among the four evaluators after each evaluating 2,100 sentences. Six training experiments were carried out. Experiments 1-3 varied the quality threshold distinguishing Good from Bad. Experiment 4 compared manual and automatic feature selection methods. Experiment 5 excluded student translators, while Experiment 6 was restricted to professional translators. The highest F-Measure was 0.775 when the participants were limited to 17 ‘Good’ and 14 ‘Bad’ professional translators. It measured 0.774 when casual translators were included as participants. The study concluded that the prediction was possible with a two-tiered approach: one for casual and professional translators and the other for professional translators only. A Japanese language qualification, the length of Japanese language use, interest in going to opera, playing Scrabble or Contract Bridge, or familiarity with cryptic crossword puzzles were found to be influential attributes for the prediction.

peer-reviewed

Named-entity recognition (NER) plays a vital role in information extraction, question answering and text mining. Classic NER research activity has focused on tagging instances of PERSON, LOCATION and ORGANISATION in the newswire domain. New fine-grained NER (FG-NER) covers subtypes of the classic NEs. The goal of this study was to investigate an FG-NER scenario with a set of new specific NEs (SNEs) typical to a new restricted journalistic domain. Reports on birth of animals in zoos were identified as such a productive domain. A 700-document corpus (241K tokens) named ZooBirth was compiled from a newspaper archive and annotated. It contained 2,811 instances of the ten most frequent numerical SNEs shortlisted from 43 candidates. Using Conditional Random Fields allowed testing positional and orderwithin- document features which were hypothesized to improve tagging SNEs. In support of positional features, analysis of distribution of SNEs within documents yielded SNE-specific patterns. The feature token position produced statistically significant but modest improvement in the case of two SNEs (82.2 to 84.4 strict precision, and 59.5 to 61.1 F-measure). Order-effect features improved with statistical significance the F-measure when tagging the weight at birth (from 68.4 to 71.1 strict, and from 75.5 to 80.6 lenient). In the final stage of the study a novel technique named subtractive tagging was introduced to enrich negative examples when training CRF. When tagging the newborn animal’s date of birth and the age of its mother strict recall improved from 52.8 to 60.1 and 65.5 to 68.9, respectively, with statistical significance.

peer-reviewed

It is generally agreed that there are three different types of financial information: information in past stock prices, information that is available to all the public, and information that is both available to the public and available privately to insiders (Fama 1970; Haugen 1990; Hellstrom and Holmstrom 1998; Elton et al 2003). There is considerable debate about the possible impact that different kinds of information can have on the value of financial instruments. On the one hand, the efficient markets hypothesis (EMH) states that the price of a financial instrument properly reflects all available information immediately (Fama 1970). If security prices respond to all available information quickly, then the market is deemed efficient and no excess profits or returns can be made. On the other hand, fundamental and technical analysts argue that the market is inefficient because information disseminates slowly through the market and prices under- or over-react to the information (Haugen 1990). A number of different data sources, features, goals, and methods have been used to automatically analyse content in financial documents. However, there has been very little research undertaken in the area of automatic event phrase recognition and classification of online disclosures. Our research study focuses on content contained in Form 8-K disclosures filed on EDGAR, a system maintained by the Securities and Exchange Commission (SEC). In our research study, we developed a prototype automatic financial event phrase (FEP) recogniser and we automatically classified a small sample of 8-Ks by likely share price response, using the automatically recognised FEPs and hand-chosen keywords as features. In four comparative classification experiments, we used the C4.5 suite of programs and the SVM-Light support vector machine program. Our datasets comprised 8-Ks filed by 50 randomlychosen S&P 500 companies from 1997 to 2000 and 2005 to 2008. Our research experiments yielded some interesting findings. In an experiment on the 2005 to 2008 dataset comprising 280 8-Ks, C4.5 was able to correctly classify 63.2% of the ‘ups’1 (as against 58.2% at chance), when using FEPs and keywords. We also found that C4.5 appears to be better at identifying patterns in the training cases than SVM-Light, regardless of whether they were ‘ups’ or ‘downs’. When we compared the results from our FEP experiments with the results from two baseline approaches—n-gram classification and Naïve Bayes bag-of-words classification—we found that C4.5 using FEPs and keywords yielded marginally higher overall classification accuracy than C4.5 using n-grams or Naïve Bayes bag-of-words. A detailed description of the classification experiments is provided in the thesis, along with a discussion of the strengths and limitations of the research study. Recommendations for future work include further refinement of the FEPs and keywords, classification of larger datasets, and incorporation of additional classification variables…

non-peer-reviewed

If a system does not possess the ability to capture, store, and retrieve people names, according to their cultural requirements, it is less likely to be acceptable on the international market. Internationalisation of people names could reduce the probability of a person’s name being lost in a system, avoiding frustration, saving time, and possibly money. This study attempts to determine the extent to which the human name can be internationalised, based upon published anthroponymic data for 148 locales, by categorising them into eleven distinctly autonomous parts: definite article, common title, honorific title, nickname, by-name, particle, forename, patronymic or matronymic, surname, community name, and generational marker. This paper provides an evaluation of the effectiveness of internationalising people names; examining the challenges of terminology conflicts, the impact of subjectivity whilst pigeonholing personyms, and the consequences of decisions made. It has demonstrated that the cultural variety of human names can be expressed with the Locale Data Mark-up Language for 74% of the world’s countries. This study, which spans 1,919 anthroponymic syntactic structures, has also established, through the use of a unique form of encoding, that the extent to which the human name can be internationalised is 96.31% of the data published by Plassard (1996) and Interpol (2006). Software developers, localisation engineers, and database administrators may benefit from this paper, through recognition of this problem and understanding the potential gains from accurately handling people names within a system. The outcome of this study opens up opportunities for future research into cultural name mapping that may further enhance the Common Locale Data Repository.

non-peer-reviewed

Presented in this thesis is the design, implementation and evaluation of a finite state morphological parser for Mohawk formal nouns. Utilizing the finite state morphology software designed by Beesely and Karttunen (2003) along with three of the most comprehensive grammars for Mohawk, one from each of the major dialectal regions, a lexicon for a finite state system was created that incorporated a structure I created from cross-referencing the three sources. Since there was no formal coursework in the program providing instruction in computer programming or morphology, these skills were self-taught. In addition to the parser, a taxonomy of Mohawk prefixes and suffixes was developed for the finite state system. The challenges facing the development of Natural Language Processing tools and language-learning technologies for the Mohawk language, as a polysynthetic language are representative of the problems that other related languages in this important group experience. The research shown here demonstrates that using finite state morphology techniques that the Mohawk language’s formal nouns can be successfully described and parsed and that with further study and review that it is possible a finite state system could be expanded to include all of Mohawk nouns, verbs, and particles. This work is looking to provide greater access to the Mohawk language for the speakers and learners of the language by use in an e-dictionary and also to support projects for language tools development for other polysynthetic and under-resourced languages.