Paper: Grouping Words Using Statistical Context

ACL ID E95-1039
Title Grouping Words Using Statistical Context
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 1995

This paper describes the use of statistical analyses of untagged corpora to detect similarities and differences in the mean- ing of words in text. This work is mo- tivated by psychological as well as by computational issues. The limitations of the method of cluster analysis in as- sessing the success of such analyses are discussed, and ongoing research using an alternative unsupervised neural network approach is described.