Bootstrapping Multilingual AMR with Contextual Word Alignments

Janaki Sheth, Young-Suk Lee, Ramón Fernandez Astudillo, Tahira Naseem, Radu Florian, Salim Roukos, Todd Ward


Abstract
We develop high performance multilingual Abstract Meaning Representation (AMR) systems by projecting English AMR annotations to other languages with weak supervision. We achieve this goal by bootstrapping transformer-based multilingual word embeddings, in particular those from cross-lingual RoBERTa (XLM-R large). We develop a novel technique for foreign-text-to-English AMR alignment, using the contextual word alignment between English and foreign language tokens. This word alignment is weakly supervised and relies on the contextualized XLM-R word embeddings. We achieve a highly competitive performance that surpasses the best published results for German, Italian, Spanish and Chinese.
Anthology ID:
2021.eacl-main.30
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
394–404
Language:
URL:
https://aclanthology.org/2021.eacl-main.30
DOI:
10.18653/v1/2021.eacl-main.30
Bibkey:
Cite (ACL):
Janaki Sheth, Young-Suk Lee, Ramón Fernandez Astudillo, Tahira Naseem, Radu Florian, Salim Roukos, and Todd Ward. 2021. Bootstrapping Multilingual AMR with Contextual Word Alignments. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 394–404, Online. Association for Computational Linguistics.
Cite (Informal):
Bootstrapping Multilingual AMR with Contextual Word Alignments (Sheth et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.30.pdf