We describe two systems for text simplification using typed dependency structures, one that performs lexical and syntactic simplification, and another that performs sentence compression optimised to satisfy global text constraints such as lexical density, the ratio of difficult words, and text length. We report a substantial evaluation that demonstrates the superiority of our systems, individua...

This study compares and contrasts lexical cohesion in English and Persian abstracts of Iranian medical students’ theses to appreciate textualization processes in the two languages. For this purpose, one hundred English and Persian abstracts were selected randomly and analyzed based on Seddigh and Yarmohamadi’s (1996) lexical cohesion framework, a version of Halliday and Hasan’s (1976) and Halli...

We describe a statistical approach for modeling dialog acts in conversational speech, i.e., speechact-like units such as Statement, Question, Backchannel, Agreement, Disagreement, and Apology. Our model detects and predicts dialog acts based on lexical, collocational, and prosodic cues, as well as on the discourse coherence of the dialog act sequence. The dialog model is based on treating the d...

The focus of this work is statistical idiosyncrasy (or collocational weight) as a discriminant property of multiword expressions. We formalize and model this property, compile a 2-class dataset of MWE and non-MWE examples, and evaluate our models on this dataset. We present a possible empirical implementation of collocational weight and study its effects on identification and extraction of MWEs...

Choosing the wrong word in a machine translation or natural language generation system can convey unwanted connotations, implications, or attitudes. The choice between near-synonyms such as error, mistake, slip, and blunder — words that share the same core meaning, but differ in their nuances — can be made only if knowledge about their differences is available. We present a method to automatica...

Building a Lexical Knowledge-Base of Near-Synonym Differences Diana Inkpen Doctor of Philosophy Graduate Department of Computer Science University of Toronto 2004 Current natural language generation or machine translation systems cannot distinguish among near-synonyms—words that share the same core meaning but vary in their lexical nuances. This is due to a lack of knowledge about differences b...

This study investigates the influence of semantic incongruency on vocabulary acquisition Kurdish learners English and different factors involved in resolving such incongruency. It also examines whether level language proficiency is key facilitating learner understanding this phenomenon. To these ends, a mixed method approach that features quantitative qualitative data collection was adopted, fo...

0 Introduction Word frequency and word predictability have both been proposed in the literature as explanations for word shortening or reduction. Traditionally, these two explanations have been modeled separately. Frequency models focus on the fact that words with high use frequency are shortened compared to low frequency words, whether in the lexicon (Zipf 1929) or during phonetic production (...

Word reading is heavily influenced by the information provided by previous context. In this study, we analyzed the neurophysiological bases of sentence reading through the EEG activity elicited during reading the same word embedded in differently constraining contexts: a) a low-constraining context; b) a high-constraining semantic compositional context; c) a high-constraining collocational cont...

At “Universidad de la Sierra”, projects of the end of a course are conducted. These projects are requested to have the structure of a research paper. In order to improve the quality of the assignment and guide the students in developing such work, an intelligent tutoring system was used. In this paper, we show a web-based intelligent tutoring system (ITS) to provide student advice in structurin...