For over 30 years, reference resolution, the process of determining what a noun phrase including a pronoun refers to in written and spoken language, has been an important and on-going area of research. Most existing pronominal reference resolution algorithms and systems are designed to use syntactic information and surface features (e.g. number…

Topic models like latent Dirichlet allocation (LDA) provide a framework for analyzing large datasets where observations are collected into groups. Although topic modeling has been fruitfully applied to problems social science, biology, and computer vision, it has been most widely used to model datasets where documents are modeled as exchangeable…

Extensive knowledge of collocations is a key factor that distinguishes learners from fluent native speakers. Such knowledge is difficult to acquire simply because there is so much of it. This paper describes a system that exploits the facilities offered by digital libraries to provide a rich collocation-learning environment. The design is based on…

In this paper we describe a simple software system that allows students to practise their critical thinking skills by constructing argument maps of natural language arguments. As the students construct their maps of an argument, the system provides automatic, real time feedback on their progress. We outline the background and theoretical framework…

The three objectives of this dissertation were to develop a question type model for predicting linguistic features of responses to interview questions, create a tool for linguistic analysis of documents, and use lexical bundle analysis to identify linguistic differences between fraudulent and non-fraudulent financial reports. First, The Moffitt…

The ability to transcribe disordered speech is a vital tool for speech-language pathologists, as accurate description of a client's speech output is needed for both diagnosis and effective intervention. Clients in the speech clinic often use sounds that are not part of the target sound system and which may, in some cases, be sounds not found in…

One of the problems associated with automatic thesaurus construction is with determining the semantic relationship between word pairs. Quasi-synonyms provide a type of equivalence relationship: words are similar only for purposes of information retrieval. Determining such relationships in a thesaurus is hard to achieve automatically. The term…

E-rater[R] is an automated essay scoring system that uses natural language processing techniques to extract features from essays and to model statistically human holistic ratings. Educational Testing Service has investigated the use of e-rater, in conjunction with human ratings, to score one of the two writing tasks on the TOEFL-iBT[R] writing…

Students in introductory programming classes often articulate their questions and information needs incompletely. Consequently, the automatic classification of student questions to provide automated tutorial responses is a challenging problem. This dissertation analyzes 411 questions from an introductory Java programming course by reducing the…

Students in introductory programming classes often articulate their questions and information needs incompletely. Consequently, the automatic classification of student questions to provide automated tutorial responses is a challenging problem. This paper analyzes 411 questions from an introductory Java programming course by reducing the natural…

This paper presents a "didactic triangulation" strategy to cope with the problem of reliability of NLP applications for computer-assisted language learning (CALL) systems. It is based on the implementation of basic but well mastered NLP techniques and puts the emphasis on an adapted gearing between computable linguistic clues and didactic features…

Tutorial Dialog Systems that employ Conversational Agents (CAs) to deliver instructional content to learners in one-on-one tutoring settings have been shown to be effective in multiple learning domains by multiple research groups. Our work focuses on extending this successful learning technology to collaborative learning settings involving two or…

In this study I introduce BioFrameNet, an extension of the Berkeley FrameNet lexical database to the domain of molecular biology. I examine the syntactic and semantic combinatorial possibilities exhibited in the lexical items used in this domain in order to get a better understanding of the grammatical properties of the language used in scientific…

Radiology data, in the form of images and reports, is growing at a high rate due to the introduction of new imaging modalities, new uses of existing modalities, and the growing importance of objective image information in the diagnosis and treatment of patients. This increase has resulted in an enormous set of image data that is richly annotated…

Purpose: Image searching is a common activity for web users. Search engines offer image retrieval services based on textual queries. Previous studies have shown that web searching is more demanding when the search is not in English and does not use a Latin-based language. The aim of this paper is to explore the behaviour of the major search…