Disambiguating Sound through Context

Lexically guided retuning of visual phonetic categories.

Listeners retune the boundaries between phonetic categories to adjust to individual speakers' productions. Lexical information, for example, indicates what an unusual sound is supposed to be, and boundary retuning then enables the speaker's sound to be included in the appropriate auditory phonetic category. In this study, it was investigated whether lexical knowledge that is known to guide the ...

On the use of right context in sense-disambiguating language models

We investigate the utility of right-context (lookahead information) in incremental left-to-right language models with word sense disambiguation, and discover somewhat unexpectedly that using right-context in addition to left-context (history) may actually reduce accuracy. We employ word sense disambiguation as one component of a language model designed to allow hypothesis to be evaluated increm...

CityU-DAC: Disambiguating Sentiment-Ambiguous Adjectives within Context

This paper describes our system participating in task 18 of SemEval-2010, i.e. disambiguating SentimentAmbiguous Adjectives (SAAs). To disambiguating SAAs, we compare the machine learning-based and lexiconbased methods in our submissions: 1) Maximum entropy is used to train classifiers based on the annotated Chinese data from the NTCIR opinion analysis tasks, and the clause-level and sentence-l...

Integrating Structural Context with Local Context for Disambiguating Word Senses

Quantifying Lexical Influence: Giving Direction to Context

The relevance of context in disambiguating natural language input has been widely acknowledged in the literature. However, most attempts at formalising the intuitive notion of context tend to treat the word and its context symmetrically. We demonstrate here that traditional measures such as mutual information score are likely to overlook a significant fraction of all co-occurrence phenomena in ...