We describe a statistical approach for modeling dialogue acts in conversational speech, i.e., speechact-like units such as STATEMENT,QUESTION, BACKCHANNEL,AGREEMENT, DISAGREEMENT, and APOLOGY. Our model detects and predicts dialogue acts based on lexical, collocational, and prosodic cues, as well as on the discourse coherence of the dialogue act sequence. The dialogue model is based on treating...

This study was an examination of the relationship of lexical richness to the quality of ESL learners’ oral narratives. A computational system was designed to automate the measurement of three dimensions of lexical richness, i.e., lexical density, sophistication, and variation, using 25 different metrics proposed in the language acquisition literature. This system was used to analyze large-scale...

Abstract The knowledge of medium-strength and field-specific collocations is a prerequisite for sounding native-like as such an essential skill to have future translators. While students are usually familiar with the use idioms fixed expressions, they may struggle recognizing also producing collocations, especially ones do not encounter enough frequency. They tend overuse certain common word co...

Semantic Representations of Near-Synonyms for Automatic Lexical Choice Philip Edmonds Doctor of Philosophy Graduate Department of Computer Science University of Toronto 1999 We develop a new computational model for representing the fine-grained meanings of nearsynonyms and the differences between them. We also develop a sophisticated lexical-choice process that can decide which of several near-...

The extent to which a symbolic time–series (a sequence of sounds or letters) is a typical word of a language, referred to as WORDLIKENESS, has been shown to have effects in speech perception and production, reading proficiency, lexical development and lexical access, short–term and long–term verbal memory. Two quantitative models have been suggested to account for these effects: serial phonotac...

Feature selection in Word Sense Disambiguation (WSD) is as important as the selection of algorithm to remove sense ambiguity. Bag-of-word (BoW) features comprise the information of neighbors around the ambiguous target word without considering any relation between words. In this study, we investigate the effect of BoW features and Bag-of-bigrams (BoB) on Turkish WSD and compare the results with...

This study investigated whether Japanese listeners learning English employ two types of lexical information (word frequency and neighborhood density) when they recognize English words. English words recorded by a native speaker of English and a native speaker of Japanese were presented to Japanese university students in a noise condition. The results of word recognition scores showed that Japan...

Most of the validation studies conducted across varying test application contexts are usually framed within the traditional conceptualization of validity and therefore lack a comprehensive framework to focus on test score interpretations and test score use. This study aimed at developing and validating a collocational behavior test (CBT), drawing on Kane's argument-based approach to validity. F...