Abstract
Despite the impressive quality improvements yielded by neural machine translation (NMT) systems, controlling their translation output to adhere to user-provided terminology constraints remains an open problem. We describe our approach to constrained neural decoding based on finite-state machines and multi-stack decoding which supports target-side constraints as well as constraints with corresponding aligned input text spans. We demonstrate the performance of our framework on multiple translation tasks and motivate the need for constrained decoding with attentions as a means of reducing misplacement and duplication when translating user constraints.- Anthology ID:
- N18-2081
- Volume:
- Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Editors:
- Marilyn Walker, Heng Ji, Amanda Stent
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 506–512
- Language:
- URL:
- https://aclanthology.org/N18-2081
- DOI:
- 10.18653/v1/N18-2081
- Cite (ACL):
- Eva Hasler, Adrià de Gispert, Gonzalo Iglesias, and Bill Byrne. 2018. Neural Machine Translation Decoding with Terminology Constraints. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 506–512, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- Neural Machine Translation Decoding with Terminology Constraints (Hasler et al., NAACL 2018)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/N18-2081.pdf