The necessity of syntactic parsing for semantic role labeling

Vasin Punyakanok, Dan Roth, Wen Tau Yih

Research output: Contribution to journalConference articlepeer-review

Abstract

We provide an experimental study of the role of syntactic parsing in semantic role labeling. Our conclusions demonstrate that syntactic parse information is clearly most relevant in the very first stage - the pruning stage. In addition, the quality of the pruning stage cannot be determined solely based on its recall and precision. Instead it depends on the characteristics of the output candidates that make downstream problems easier or harder. Motivated by this observation, we suggest an effective and simple approach of combining different semantic role labeling systems through joint inference, which significantly improves the performance.

Original languageEnglish (US)
Pages (from-to)1117-1123
Number of pages7
JournalIJCAI International Joint Conference on Artificial Intelligence
StatePublished - Dec 1 2005
Event19th International Joint Conference on Artificial Intelligence, IJCAI 2005 - Edinburgh, United Kingdom
Duration: Jul 30 2005Aug 5 2005

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'The necessity of syntactic parsing for semantic role labeling'. Together they form a unique fingerprint.

Cite this