Joint Parsing and Semantic Role Labeling

Proceedings of the 9th Conference on Computational Natural Language Learning (CoNLL), pages 225–228, Ann Arbor, June 2005. c⃝2005 Association for Computational Linguistics Joint Parsing and Semantic Role Labeling Charles Sutton and Andrew McCallum Department of Computer Science University of Massachusetts Amherst, MA 01003 USA {casutton,mccallum}@cs.umass.edu Abstract A striking feature of human syntactic pro- cessing is that it is context-dependent, that is, it seems to take into account seman- tic information from the discourse con- text and world knowledge. In this paper, we attempt to use this insight to bridge the gap between SRL results from gold parses and from automatically-generated parses. To do this, we jointly perform parsing and semantic role labeling, using a probabilistic SRL system to rerank the results of a probabilistic parser. Our cur- rent results are negative, because a locally- trained SRL model can return inaccurate probability estimates. 1 Introduction Although much effort has gone into developing statistical parsing models and they have improved steadily over the years, in many applications that use parse trees errors made by the parser are a ma- jor source of errors in the final output. A promising approach to this problem is to perform both pars- ing and the higher-level task in a single, joint prob- abilistic model. This not only allows uncertainty about the parser output to be carried upward, such as through an k-best list, but also allows informa- tion from higher-level processing to improve pars- ing. For example, Miller et al. (2000) showed that performing parsing and information extraction in a joint model improves performance on both tasks. In particular, one suspects that attachment decisions, which are both notoriously hard and extremely im- portant for semantic analysis, could benefit greatly from input from higher-level semantic analysis. The recent interest in semantic role labeling pro- vides an opportunity to explore how higher-level se- mantic information can inform syntactic parsing. In previous work, it has been shown that SRL systems that use full parse information perform better than those that use shallow parse information, but that machine-generated parses still perform much worse than human-corrected gold parses. The goal of this investigation is to narrow the gap between SRL results from gold parses and from au- tomatic parses. We aim to do this by jointly perform- ing parsing and semantic role labeling in a single probabilistic model. In both parsing and SRL, state- of-the-art systems are probabilistic; therefore, their predictions can be combined in a principled way by multiplying probabilities. In this paper, we rerank the k-best parse trees from a probabilistic parser us- ing an SRL system. We compare two reranking ap- proaches, one that linearly weights the log proba- bilities, and the other that learns a reranker over parse trees and SRL frames in the manner of Collins (2000). Currently, neither method performs better than simply selecting the top predicted parse tree. We discuss some of the reasons for this; one reason be- ing that the ranking over parse trees induced by the semantic role labeling score is …

Content truncated to 500 words