Abstract
A popular natural language processing task decades ago, word alignment has been dominated until recently by GIZA++, a statistical method based on the 30-year-old IBM models. New methods that outperform GIZA++ primarily rely on large machine translation models, massively multilingual language models, or supervision from GIZA++ alignments itself. We introduce Embedding-Enhanced GIZA++, and outperform GIZA++ without any of the aforementioned factors. Taking advantage of monolingual embedding spaces of source and target language only, we exceed GIZA++’s performance in every tested scenario for three languages pairs. In the lowest-resource setting, we outperform GIZA++ by 8.5, 10.9, and 12 AER for RoEn, De-En, and En-Fr, respectively. We release our code at www.blind-review.code.- Anthology ID:
- 2022.amta-research.20
- Volume:
- Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)
- Month:
- September
- Year:
- 2022
- Address:
- Orlando, USA
- Editors:
- Kevin Duh, Francisco Guzmán
- Venue:
- AMTA
- SIG:
- Publisher:
- Association for Machine Translation in the Americas
- Note:
- Pages:
- 264–273
- Language:
- URL:
- https://aclanthology.org/2022.amta-research.20
- DOI:
- Cite (ACL):
- Kelly Marchisio, Conghao Xiong, and Philipp Koehn. 2022. Embedding-Enhanced GIZA++: Improving Low-Resource Word Alignment Using Embeddings. In Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Volume 1: Research Track), pages 264–273, Orlando, USA. Association for Machine Translation in the Americas.
- Cite (Informal):
- Embedding-Enhanced GIZA++: Improving Low-Resource Word Alignment Using Embeddings (Marchisio et al., AMTA 2022)
- PDF:
- https://preview.aclanthology.org/corrections-2024-07/2022.amta-research.20.pdf