Extracting Semantic Representations from Word Co-occurrence Statistics: A Computational Study

John Bullinaria, JP Levy

Research output: Contribution to journalArticle

366 Citations (Scopus)


The idea that at least some aspects of word meaning can be induced from patterns of word co-occurrence is becoming increasingly popular. However, there is less agreement about the precise computations involved, and the appropriate tests to distinguish between the various possibilities. It is important that the effect of the relevant design choices and parameter values are understood if psychological models using these methods are to be reliably evaluated and compared. In this article, we present a systematic exploration of the principal computational possibilities for formulating and validating representations of word meanings from word co-occurrence statistics. We find that, once we have identified the best procedures, a very simple approach is surprisingly successful and robust over a range of psychologically relevant evaluation measures.
Original languageEnglish
Pages (from-to)510-526
Number of pages17
JournalBehavior Research Methods
Issue number3
Publication statusPublished - 1 Aug 2007


Dive into the research topics of 'Extracting Semantic Representations from Word Co-occurrence Statistics: A Computational Study'. Together they form a unique fingerprint.

Cite this