Paper: Unsupervised Semantic Role Induction via Split-Merge Clustering

ACL ID P11-1112
Title Unsupervised Semantic Role Induction via Split-Merge Clustering
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011

In this paper we describe an unsupervised method for semantic role induction which holds promise for relieving the data acqui- sition bottleneck associated with supervised role labelers. We present an algorithm that it- eratively splits and merges clusters represent- ing semantic roles, thereby leading from an initial clustering to a final clustering of bet- ter quality. The method is simple, surpris- ingly effective, and allows to integrate lin- guistic knowledge transparently. By com- bining role induction with a rule-based com- ponent for argument identification we obtain an unsupervised end-to-end semantic role la- beling system. Evaluation on the CoNLL 2008 benchmark dataset demonstrates that our method outperforms competitive unsuper- vised approaches by a wide margin.