TY - GEN
T1 - Starting from scratch in semantic role labeling
AU - Connor, Michael
AU - Gertner, Yael
AU - Fisher, Cynthia
AU - Roth, Dan
N1 - Funding Information:
This research is supported by NSF grant BCS-0620257 and NIH grant R01-HD054448.
Publisher Copyright:
© 2010 Association for Computational Linguistics.
PY - 2010
Y1 - 2010
N2 - A fundamental step in sentence comprehension involves assigning semantic roles to sentence constituents. To accomplish this, the listener must parse the sentence, find constituents that are candidate arguments, and assign semantic roles to those constituents. Each step depends on prior lexical and syntactic knowledge. Where do children learning their first languages begin in solving this problem? In this paper we focus on the parsing and argument-identification steps that precede Semantic Role Labeling (SRL) training. We combine a simplified SRL with an unsupervised HMM part of speech tagger, and experiment with psycholinguistically-motivated ways to label clusters resulting from the HMM so that they can be used to parse input for the SRL system. The results show that proposed shallow representations of sentence structure are robust to reductions in parsing accuracy, and that the contribution of alternative representations of sentence structure to successful semantic role labeling varies with the integrity of the parsing and argument-identification stages.
AB - A fundamental step in sentence comprehension involves assigning semantic roles to sentence constituents. To accomplish this, the listener must parse the sentence, find constituents that are candidate arguments, and assign semantic roles to those constituents. Each step depends on prior lexical and syntactic knowledge. Where do children learning their first languages begin in solving this problem? In this paper we focus on the parsing and argument-identification steps that precede Semantic Role Labeling (SRL) training. We combine a simplified SRL with an unsupervised HMM part of speech tagger, and experiment with psycholinguistically-motivated ways to label clusters resulting from the HMM so that they can be used to parse input for the SRL system. The results show that proposed shallow representations of sentence structure are robust to reductions in parsing accuracy, and that the contribution of alternative representations of sentence structure to successful semantic role labeling varies with the integrity of the parsing and argument-identification stages.
UR - http://www.scopus.com/inward/record.url?scp=85118429802&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85118429802&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85118429802
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 989
EP - 998
BT - ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Conference Proceedings
A2 - Hajic, Jan
A2 - Carberry, Sandra
A2 - Clark, Stephen
PB - Association for Computational Linguistics (ACL)
T2 - 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010
Y2 - 11 July 2010 through 16 July 2010
ER -