Abstract
This paper presents an approach to project FrameNet annotations into other languages using attention-based neural machine translation (NMT) models. The idea is to use an NMT encoder-decoder attention matrix to propose a word-to-word correspondence between the source and the target language. We combine this word alignment along with a set of simple rules to securely project the FrameNet annotations into the target language. We successfully implemented, evaluated and analyzed this technique on the English-to-French configuration. First, we analyze the obtained FrameNet lexicon qualitatively. Then, we use existing French FrameNet corpora to assert the quality of the translation. Finally, we trained a BERT-based FrameNet parser using the projected annotations and compared it to a BERT baseline. Results show substantial improvements in the French language, giving evidence to support that our approach could help to propagate FrameNet data-set on other languages.- Anthology ID:
- 2020.framenet-1.6
- Volume:
- Proceedings of the International FrameNet Workshop 2020: Towards a Global, Multilingual FrameNet
- Month:
- May
- Year:
- 2020
- Address:
- Marseille, France
- Editors:
- Tiago T. Torrent, Collin F. Baker, Oliver Czulo, Kyoko Ohara, Miriam R. L. Petruck
- Venue:
- Framenet
- SIG:
- Publisher:
- European Language Resources Association
- Note:
- Pages:
- 41–47
- Language:
- English
- URL:
- https://aclanthology.org/2020.framenet-1.6
- DOI:
- Cite (ACL):
- Gabriel Marzinotto. 2020. FrameNet Annotations Alignment using Attention-based Machine Translation. In Proceedings of the International FrameNet Workshop 2020: Towards a Global, Multilingual FrameNet, pages 41–47, Marseille, France. European Language Resources Association.
- Cite (Informal):
- FrameNet Annotations Alignment using Attention-based Machine Translation (Marzinotto, Framenet 2020)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2020.framenet-1.6.pdf