Janaki Sheth
2021
Bootstrapping Multilingual AMR with Contextual Word Alignments
Janaki Sheth
|
Young-Suk Lee
|
Ramón Fernandez Astudillo
|
Tahira Naseem
|
Radu Florian
|
Salim Roukos
|
Todd Ward
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
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.
Search
Co-authors
- Young-Suk Lee 1
- Ramón Fernandez Astudillo 1
- Tahira Naseem 1
- Radu Florian 1
- Salim Roukos 1
- show all...
Venues
- eacl1