Abstract
A multilingual translation model enables a single model to handle multiple languages. However, the translation qualities of unlearned language pairs (i.e., zero-shot translation qualities) are still poor. By contrast, pivot translation translates source texts into target ones via a pivot language such as English, thus enabling machine translation without parallel texts between the source and target languages. In this paper, we perform pivot translation using a multilingual model and compare it with direct translation. We improve the translation quality without using parallel texts of direct translation by fine-tuning the model with machine-translated pseudo-translations. We also discuss what type of parallel texts are suitable for effectively improving the translation quality in multilingual pivot translation.- Anthology ID:
- 2023.mtsummit-research.29
- Volume:
- Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track
- Month:
- September
- Year:
- 2023
- Address:
- Macau SAR, China
- Editors:
- Masao Utiyama, Rui Wang
- Venue:
- MTSummit
- SIG:
- Publisher:
- Asia-Pacific Association for Machine Translation
- Note:
- Pages:
- 348–359
- Language:
- URL:
- https://aclanthology.org/2023.mtsummit-research.29
- DOI:
- Cite (ACL):
- Kenji Imamura, Masao Utiyama, and Eiichiro Sumita. 2023. Pivot Translation for Zero-resource Language Pairs Based on a Multilingual Pretrained Model. In Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track, pages 348–359, Macau SAR, China. Asia-Pacific Association for Machine Translation.
- Cite (Informal):
- Pivot Translation for Zero-resource Language Pairs Based on a Multilingual Pretrained Model (Imamura et al., MTSummit 2023)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2023.mtsummit-research.29.pdf