Abstract
This paper describes the use of statistical analyses of untagged corpora to detect similarities and differences in the meaning of words in text. This work is motivated by psychological as well as by computational issues. The limitations of the method of cluster analysis in assessing the success of such analyses are discussed, and ongoing research using an alternative unsupervised neural network approach is described.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have