Paper: Diathesis alternation approximation for verb clustering

ACL ID P13-2129
Title Diathesis alternation approximation for verb clustering
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013

Although diathesis alternations have been used as features for manual verb clas- sification, and there is recent work on incorporating such features in computa- tional models of human language acquisi- tion, work on large scale verb classifica- tion has yet to examine the potential for using diathesis alternations as input fea- tures to the clustering process. This pa- per proposes a method for approximating diathesis alternation behaviour in corpus data and shows, using a state-of-the-art verb clustering system, that features based on alternation approximation outperform those based on independent subcategoriza- tion frames. Our alternation-based ap- proach is particularly adept at leveraging information from less frequent data.