Syntax-aware Neural Semantic Role Labeling with Supertags

Jungo Kasai, Dan Friedman, Robert Frank, Dragomir Radev, Owen Rambow


Abstract
We introduce a new syntax-aware model for dependency-based semantic role labeling that outperforms syntax-agnostic models for English and Spanish. We use a BiLSTM to tag the text with supertags extracted from dependency parses, and we feed these supertags, along with words and parts of speech, into a deep highway BiLSTM for semantic role labeling. Our model combines the strengths of earlier models that performed SRL on the basis of a full dependency parse with more recent models that use no syntactic information at all. Our local and non-ensemble model achieves state-of-the-art performance on the CoNLL 09 English and Spanish datasets. SRL models benefit from syntactic information, and we show that supertagging is a simple, powerful, and robust way to incorporate syntax into a neural SRL system.
Anthology ID:
N19-1075
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
701–709
Language:
URL:
https://aclanthology.org/N19-1075
DOI:
10.18653/v1/N19-1075
Bibkey:
Cite (ACL):
Jungo Kasai, Dan Friedman, Robert Frank, Dragomir Radev, and Owen Rambow. 2019. Syntax-aware Neural Semantic Role Labeling with Supertags. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 701–709, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Syntax-aware Neural Semantic Role Labeling with Supertags (Kasai et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1075.pdf
Code
 jungokasai/stagging_srl