TY - GEN
T1 - Cross-domain Generalization for AMR Parsing
AU - Bai, Xuefeng
AU - Yang, Sen
AU - Cui, Leyang
AU - Song, Linfeng
AU - Zhang, Yue
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85149437131
U2 - 10.18653/v1/2022.emnlp-main.749
DO - 10.18653/v1/2022.emnlp-main.749
M3 - 会议稿件
AN - SCOPUS:85149437131
T3 - Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
SP - 10907
EP - 10921
BT - Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
A2 - Goldberg, Yoav
A2 - Kozareva, Zornitsa
A2 - Zhang, Yue
PB - Association for Computational Linguistics (ACL)
T2 - 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
Y2 - 7 December 2022 through 11 December 2022
ER -