Code-Switching for Enhancing NMT with Pre-Specified Translation
Kai Song, Yue Zhang, Heng Yu, Weihua Luo, Kun Wang, Min Zhang
Abstract
Leveraging user-provided translation to constrain NMT has practical significance. Existing methods can be classified into two main categories, namely the use of placeholder tags for lexicon words and the use of hard constraints during decoding. Both methods can hurt translation fidelity for various reasons. We investigate a data augmentation method, making code-switched training data by replacing source phrases with their target translations. Our method does not change the MNT model or decoding algorithm, allowing the model to learn lexicon translations by copying source-side target words. Extensive experiments show that our method achieves consistent improvements over existing approaches, improving translation of constrained words without hurting unconstrained words.- Anthology ID:
- N19-1044
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Editors:
- Jill Burstein, Christy Doran, Thamar Solorio
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 449–459
- Language:
- URL:
- https://aclanthology.org/N19-1044
- DOI:
- 10.18653/v1/N19-1044
- Cite (ACL):
- Kai Song, Yue Zhang, Heng Yu, Weihua Luo, Kun Wang, and Min Zhang. 2019. Code-Switching for Enhancing NMT with Pre-Specified Translation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 449–459, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Code-Switching for Enhancing NMT with Pre-Specified Translation (Song et al., NAACL 2019)
- PDF:
- https://preview.aclanthology.org/ingest-2024-clasp/N19-1044.pdf
- Code
- batman2013/e-commerce_test_sets