Paper: Unsupervised Semantic Role Induction with Graph Partitioning

ACL ID D11-1122
Title Unsupervised Semantic Role Induction with Graph Partitioning
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2011
Authors

In this paper we present a method for unsuper- vised semantic role induction which we for- malize as a graph partitioning problem. Ar- gument instances of a verb are represented as vertices in a graph whose edge weights quan- tify their role-semantic similarity. Graph par- titioning is realized with an algorithm that it- eratively assigns vertices to clusters based on the cluster assignments of neighboring ver- tices. Our method is algorithmically and con- ceptually simple, especially with respect to how problem-specific knowledge is incorpo- rated into the model. Experimental results on the CoNLL 2008 benchmark dataset demon- strate that our model is competitive with other unsupervised approaches in terms of F1 whilst attaining significantly higher cluster purity.