Previous abstract | Contents | Next abstract
This paper introduces PhraseNet, a context-sensitive lexical semantic knowledge base system. Based on the supposition that semantic proximity is not simply a relation between two words in isolation, but rather a relation between them in their context, English nouns and verbs, along with contexts they appear in, are organized in PhraseNet into Consets; Consets capture the underlying lexical concept, and are connected with several semantic relations that respect contextually sensitive lexical information. PhraseNet makes use of WordNet as an important knowledge source. It enhances a WordNet synset with its contextual information and refines its relational structure by maintaining only those relations that respect contextual constraints. The contextual information allows for supporting more functionalities compared with those of WordNet. Natural language researchers as well as linguists and language learners can gain from accessing PhraseNet with a word token and its context, to retrieve relevant semantic information. We describe the design and construction of PhraseNet and give preliminary experimental evidence to its usefulness for NLP researches.