Joint Arc-factored Parsing of Syntactic and Semantic Dependencies

Xavier Lluís,Xavier Carreras,Lluís Màrquez

doi:10.1162/tacl_a_00222

Abstract

In this paper we introduce a joint arc-factored model for syntactic and semantic dependency parsing. The semantic role labeler predicts the full syntactic paths that connect predicates with their arguments. This process is framed as a linear assignment task, which allows to control some well-formedness constraints. For the syntactic part, we define a standard arc-factored dependency model that predicts the full syntactic tree. Finally, we employ dual decomposition techniques to produce consistent syntactic and predicate-argument structures while searching over a large space of syntactic configurations. In experiments on the CoNLL-2009 English benchmark we observe very competitive results.

Highlights

Semantic role labeling (SRL) is the task of identifying the arguments of lexical predicates in a sentence and labeling them with semantic roles (Gildea and Jurafsky, 2002; Marquez et al, 2008)
Semantic predicate-argument relations are evaluated with precision, recall and F1 measure at the level of labeled semantic dependencies
One is to predict the local syntactic structure that links a predicate with its arguments, and seek agreement with the full syntactic structure using dual decomposition techniques

Summary

Introduction

Semantic role labeling (SRL) is the task of identifying the arguments of lexical predicates in a sentence and labeling them with semantic roles (Gildea and Jurafsky, 2002; Marquez et al, 2008). More recent work has proposed parsing models that predict syntactic structure augmented with semantic predicate-argument relations (Surdeanu et al, 2008; Hajicet al., 2009; Johansson, 2009; Titov et al, 2009; Lluıs et al, 2009), which is the focus of this paper. These joint models should favor the syntactic structure that is most consistent with the semantic predicate-argument structures of a sentence. These models can exploit syntactic and semantic features simultaneously, and could potentially improve the accuracy for both syntactic and semantic relations

Objectives

Methods

Results

Conclusion