Choosing the word most typical in context using a lexical co-occurrence network

Abstract

This paper presents a partial solution to a component of the problem of lexical choice: choosing the synonym most typical, or expected, in context. We apply a new statistical approach to representing the context of a word through lexical co-occurrence networks. The implementation was trained and evaluated on a large corpus, and results show that the inclusion of second-order co-occurrence relations improves the performance of our implemented lexical choice program.

A framework for understanding Latent Semantic Indexing (LSI) performance

“…Philip Edmonds shows the benefits of using second-and third-order co-occurrence in (Edmonds, 1997). The application described selects the most appropriate term when a context (such as a sentence) is provided.…”

A statistical model for near-synonym choice

“…We compare our results with those of Edmonds [1997], whose solution used the texts from the year 1989 of the Wall Street Journal (WSJ) to build a lexical cooccurrence network for each of the seven groups of near-synonyms from Table II. The network included second-order co-occurrences.…”

A statistical model for near-synonym choice

“…In fact, the only work that addresses exactly the same task is that of Edmonds [1997], as far as we are aware. Edmonds gives a solution based on a lexical cooccurrence network that included second-order co-occurrences.…”