Finding word substitutions using a distributional similarity baseline and immediate context overlap

Aurelie Herbelot
2009 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop on - EACL '09   unpublished
This paper deals with the task of finding generally applicable substitutions for a given input term. We show that the output of a distributional similarity system baseline can be filtered to obtain terms that are not simply similar but frequently substitutable. Our filter relies on the fact that when two terms are in a common entailment relation, it should be possible to substitute one for the other in their most frequent surface contexts. Using the Google 5-gram corpus to find such
more » ... nd such characteristic contexts, we show that for the given task, our filter improves the precision of a distributional similarity system from 41% to 56% on a test set comprising common transitive verbs.
doi:10.3115/1609179.1609183 fatcat:l6g4fhl2j5aojgmkwdgqam26l4