Choosing the Word Most Typical in Context Using a Lexical Co-Occurrence Network

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.

• Type: Conference
• Year: 1997
• Where: ACL
• Authors: Philip Edmonds
• Keywords: ACL 1997, ACL 2007, Implemented Lexical Choice, Lexical Choice, Lexical Co-occurrence Networks