NAIST-NICT-TIT WMT22 General MT Task Submission
Hiroyuki Deguchi, Kenji Imamura, Masahiro Kaneko, Yuto Nishida, Yusuke Sakai, Justin Vasselli, Huy Hien Vu, Taro Watanabe
Abstract
In this paper, we describe our NAIST-NICT-TIT submission to the WMT22 general machine translation task. We participated in this task for the English ↔ Japanese language pair.Our system is characterized as an ensemble of Transformer big models, k-nearest-neighbor machine translation (kNN-MT) (Khandelwal et al., 2021), and reranking.In our translation system, we construct the datastore for kNN-MT from back-translated monolingual data and integrate kNN-MT into the ensemble model. We designed a reranking system to select a translation from the n-best translation candidates generated by the translation system. We also use a context-aware model to improve the document-level consistency of the translation.- Anthology ID:
- 2022.wmt-1.16
- Volume:
- Proceedings of the Seventh Conference on Machine Translation (WMT)
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates (Hybrid)
- Venue:
- WMT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 244–250
- Language:
- URL:
- https://aclanthology.org/2022.wmt-1.16
- DOI:
- Cite (ACL):
- Hiroyuki Deguchi, Kenji Imamura, Masahiro Kaneko, Yuto Nishida, Yusuke Sakai, Justin Vasselli, Huy Hien Vu, and Taro Watanabe. 2022. NAIST-NICT-TIT WMT22 General MT Task Submission. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 244–250, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- NAIST-NICT-TIT WMT22 General MT Task Submission (Deguchi et al., WMT 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.wmt-1.16.pdf