Inducing and Using Alignments for Transition-based AMR Parsing

Andrew Drozdov, Jiawei Zhou, Radu Florian, Andrew McCallum, Tahira Naseem, Yoon Kim, Ramón Astudillo


Abstract
Transition-based parsers for Abstract Meaning Representation (AMR) rely on node-to-word alignments. These alignments are learned separately from parser training and require a complex pipeline of rule-based components, pre-processing, and post-processing to satisfy domain-specific constraints. Parsers also train on a point-estimate of the alignment pipeline, neglecting the uncertainty due to the inherent ambiguity of alignment. In this work we explore two avenues for overcoming these limitations. First, we propose a neural aligner for AMR that learns node-to-word alignments without relying on complex pipelines. We subsequently explore a tighter integration of aligner and parser training by considering a distribution over oracle action sequences arising from aligner uncertainty. Empirical results show this approach leads to more accurate alignments and generalization better from the AMR2.0 to AMR3.0 corpora. We attain a new state-of-the art for gold-only trained models, matching silver-trained performance without the need for beam search on AMR3.0.
Anthology ID:
2022.naacl-main.80
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1086–1098
Language:
URL:
https://aclanthology.org/2022.naacl-main.80
DOI:
10.18653/v1/2022.naacl-main.80
Bibkey:
Cite (ACL):
Andrew Drozdov, Jiawei Zhou, Radu Florian, Andrew McCallum, Tahira Naseem, Yoon Kim, and Ramón Astudillo. 2022. Inducing and Using Alignments for Transition-based AMR Parsing. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1086–1098, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Inducing and Using Alignments for Transition-based AMR Parsing (Drozdov et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.80.pdf
Video:
 https://aclanthology.org/2022.naacl-main.80.mp4
Code
 IBM/transition-amr-parser