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.
BibTeX
@inproceedings{drozdov-etal-2022-inducing,
title = "Inducing and Using Alignments for Transition-based {AMR} Parsing",
author = "Drozdov, Andrew and
Zhou, Jiawei and
Florian, Radu and
McCallum, Andrew and
Naseem, Tahira and
Kim, Yoon and
Astudillo, Ram{\'o}n",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.80/",
doi = "10.18653/v1/2022.naacl-main.80",
pages = "1086--1098"
}