Paper: Feature Vector Quality And Distributional Similarity

ACL ID C04-1036
Title Feature Vector Quality And Distributional Similarity
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2004
Authors

We suggest a new goal and evaluation criterion for word similarity measures. The new criterion - meaning-entailing substitutability - fits the needs of semantic-oriented NLP applications and can be evaluated directly (independent of an application) at a good level of human agreement. Motivated by this semantic criterion we analyze the empirical quality of distributional word feature vectors and its impact on word similarity results, proposing an objective measure for evaluating feature vector quality. Finally, a novel feature weighting and se- lection function is presented, which yields superior feature vectors and better word similarity perform- ance.