Skip to main navigation Skip to search Skip to main content

Cross-domain Generalization for AMR Parsing

  • Xuefeng Bai
  • , Sen Yang
  • , Leyang Cui
  • , Linfeng Song
  • , Yue Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publicationProceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
EditorsYoav Goldberg, Zornitsa Kozareva, Yue Zhang
PublisherAssociation for Computational Linguistics (ACL)
Pages10907-10921
Number of pages15
ISBN (Electronic)9781959429401
DOIs
StatePublished - 2022
Externally publishedYes
Event2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022 - Hybrid, Abu Dhabi, United Arab Emirates
Duration: 7 Dec 202211 Dec 2022

Publication series

NameProceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

Conference

Conference2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
Country/TerritoryUnited Arab Emirates
CityHybrid, Abu Dhabi
Period7/12/2211/12/22

Fingerprint

Dive into the research topics of 'Cross-domain Generalization for AMR Parsing'. Together they form a unique fingerprint.

Cite this