Semantic Role Labeling as Syntactic Dependency Parsing

Tianze Shi, Igor Malioutov, Ozan Irsoy


Abstract
We reduce the task of (span-based) PropBank-style semantic role labeling (SRL) to syntactic dependency parsing. Our approach is motivated by our empirical analysis that shows three common syntactic patterns account for over 98% of the SRL annotations for both English and Chinese data. Based on this observation, we present a conversion scheme that packs SRL annotations into dependency tree representations through joint labels that permit highly accurate recovery back to the original format. This representation allows us to train statistical dependency parsers to tackle SRL and achieve competitive performance with the current state of the art. Our findings show the promise of syntactic dependency trees in encoding semantic role relations within their syntactic domain of locality, and point to potential further integration of syntactic methods into semantic role labeling in the future.
Anthology ID:
2020.emnlp-main.610
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7551–7571
Language:
URL:
https://aclanthology.org/2020.emnlp-main.610
DOI:
10.18653/v1/2020.emnlp-main.610
Bibkey:
Cite (ACL):
Tianze Shi, Igor Malioutov, and Ozan Irsoy. 2020. Semantic Role Labeling as Syntactic Dependency Parsing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7551–7571, Online. Association for Computational Linguistics.
Cite (Informal):
Semantic Role Labeling as Syntactic Dependency Parsing (Shi et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.610.pdf
Video:
 https://slideslive.com/38939017
Code
 bloomberg/emnlp20_depsrl
Data
Universal Dependencies