Neural semi-Markov CRF for Monolingual Word Alignment

Wuwei Lan, Chao Jiang, Wei Xu


Abstract
Monolingual word alignment is important for studying fine-grained editing operations (i.e., deletion, addition, and substitution) in text-to-text generation tasks, such as paraphrase generation, text simplification, neutralizing biased language, etc. In this paper, we present a novel neural semi-Markov CRF alignment model, which unifies word and phrase alignments through variable-length spans. We also create a new benchmark with human annotations that cover four different text genres to evaluate monolingual word alignment models in more realistic settings. Experimental results show that our proposed model outperforms all previous approaches for monolingual word alignment as well as a competitive QA-based baseline, which was previously only applied to bilingual data. Our model demonstrates good generalizability to three out-of-domain datasets and shows great utility in two downstream applications: automatic text simplification and sentence pair classification tasks.
Anthology ID:
2021.acl-long.531
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6815–6828
Language:
URL:
https://aclanthology.org/2021.acl-long.531
DOI:
10.18653/v1/2021.acl-long.531
Bibkey:
Cite (ACL):
Wuwei Lan, Chao Jiang, and Wei Xu. 2021. Neural semi-Markov CRF for Monolingual Word Alignment. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 6815–6828, Online. Association for Computational Linguistics.
Cite (Informal):
Neural semi-Markov CRF for Monolingual Word Alignment (Lan et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2021.acl-long.531.pdf
Video:
 https://preview.aclanthology.org/ingest-acl-2023-videos/2021.acl-long.531.mp4
Code
 chaojiang06/neural-Jacana
Data
GLUEMRPCMultiNLINewselaPITSICKSNLIWikiQA