Cross-domain Generalization for AMR Parsing
Xuefeng Bai, Sen Yang, Leyang Cui, Linfeng Song, Yue Zhang
Abstract
Abstract Meaning Representation (AMR) parsing aims to predict an AMR graph from textual input. Recently, there has been notable growth in AMR parsing performance. However, most existing work focuses on improving the performance in the specific domain, ignoring the potential domain dependence of AMR parsing systems. To address this, we extensively evaluate five representative AMR parsers on five domains and analyze challenges to cross-domain AMR parsing. We observe that challenges to cross-domain AMR parsing mainly arise from the distribution shift of words and AMR concepts. Based on our observation, we investigate two approaches to reduce the domain distribution divergence of text and AMR features, respectively. Experimental results on two out-of-domain test sets show the superiority of our method.
BibTeX
@inproceedings{bai-etal-2022-cross,
title = "Cross-domain Generalization for {AMR} Parsing",
author = "Bai, Xuefeng and
Yang, Sen and
Cui, Leyang and
Song, Linfeng and
Zhang, Yue",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.749/",
doi = "10.18653/v1/2022.emnlp-main.749",
pages = "10907--10921"
}