tailieunhanh - Báo cáo khoa học: "A Bayesian Approach to Unsupervised Semantic Role Induction"

We introduce two Bayesian models for unsupervised semantic role labeling (SRL) task. The models treat SRL as clustering of syntactic signatures of arguments with clusters corresponding to semantic roles. The first model induces these clusterings independently for each predicate, exploiting the Chinese Restaurant Process (CRP) as a prior. In a more refined hierarchical model, we inject the intuition that the clusterings are similar across different predicates, even though they are not necessarily identical. This intuition is encoded as a distance-dependent CRP with a distance between two syntactic signatures indicating how likely they are to correspond to a single semantic. | A Bayesian Approach to Unsupervised Semantic Role Induction Ivan Titov Alexandre Klementiev Saarland University Saarbriicken Germany titov aklement @ Abstract We introduce two Bayesian models for unsupervised semantic role labeling SRL task. The models treat SRL as clustering of syntactic signatures of arguments with clusters corresponding to semantic roles. The first model induces these clusterings independently for each predicate exploiting the Chinese Restaurant Process CRP as a prior. In a more refined hierarchical model we inject the intuition that the clusterings are similar across different predicates even though they are not necessarily identical. This intuition is encoded as a distance-dependent CRP with a distance between two syntactic signatures indicating how likely they are to correspond to a single semantic role. These distances are automatically induced within the model and shared across predicates. Both models achieve state-of-the-art results when evaluated on PropBank with the coupled model consistently outperforming the factored counterpart in all experimental set-ups. 1 Introduction Semantic role labeling SRL Gildea and Juraf-sky 2002 a shallow semantic parsing task has recently attracted a lot of attention in the computational linguistic community Carreras and Marquez 2005 Surdeanu et al. 2008 Hajic et al. 2009 . The task involves prediction of predicate argument structure . both identification of arguments as well as assignment of labels according to their underlying semantic role. For example in the following sentences a ao Mary opened ai the door . b ao Mary is expected to open ai the door . c ai The door opened. d ai The door was opened ao by Mary . Mary always takes an agent role A0 for the predicate open and door is always a patient A1 . SRL representations have many potential applications in natural language processing and have recently been shown to be beneficial in question answering Shen and Lapata 2007 Kaisser .