The importance of syntactic parsing and inference in semantic role labeling

The importance of syntactic parsing and inference in semantic role labeling (2008)

Cached

Download Links

[l2r.cs.uiuc.edu]

by Vasin Punyakanok , Dan Roth , Wen-tau Yih

Venue:	COMPUTATIONAL LINGUISTICS
Citations:	28 - 13 self

Versions

Version History

Metadata Version 2

User correction supplied by mph

Datum	Value	Source
TITLE	The importance of syntactic parsing and inference in semantic role labeling	user correction
AUTHOR NAME	Vasin Punyakanok	user correction
AUTHOR AFFIL	BBN Technologies	user correction
AUTHOR NAME	Dan Roth	user correction
AUTHOR AFFIL	Department of Computer Science; University of Illinois at Urbana-Champaign	user correction
AUTHOR NAME	Wen-tau Yih	user correction
AUTHOR AFFIL	Microsoft Research	user correction
ABSTRACT	We present a general framework for semantic role labeling. The framework combines a machine learning technique with an integer linear programming based inference procedure, which incorporates linguistic and structural constraints into a global decision process. Within this framework, we study the role of syntactic parsing information in semantic role labeling. We show that full syntactic parsing information is, by far, most relevant in identifying the argument, especially, in the very first stage—the pruning stage. Surprisingly, the quality of the pruning stage cannot be solely determined based on its recall and precision. Instead, it depends on the characteristics of the output candidates that determine the difficulty of the downstream problems. Motivated by this observation, we propose an effective and simple approach of combining different semantic role labeling systems through joint inference, which significantly improves its performance. Our system has been evaluated in the CoNLL-2005 shared task on semantic role labeling, and achieves the highest F1 score among 19 participants.	user correction
YEAR	2008	INFERENCE
VENUE	COMPUTATIONAL LINGUISTICS	user correction
VENUE TYPE	JOURNAL	INFERENCE
VOLUME	6	user correction
NUMBER	9	user correction
CITATIONS	48 found	ParsCit 1.0