The University of Maryland’s Submissions to the WMT20 Chat Translation Task: Searching for More Data to Adapt Discourse-Aware Neural Machine Translation
Calvin Bao, Yow-Ting Shiue, Chujun Song, Jie Li, Marine Carpuat
Abstract
This paper describes the University of Maryland’s submissions to the WMT20 Shared Task on Chat Translation. We focus on translating agent-side utterances from English to German. We started from an off-the-shelf BPE-based standard transformer model trained with WMT17 news and fine-tuned it with the provided in-domain training data. In addition, we augment the training set with its best matches in the WMT19 news dataset. Our primary submission uses a standard Transformer, while our contrastive submissions use multi-encoder Transformers to attend to previous utterances. Our primary submission achieves 56.7 BLEU on the agent side (en→de), outperforming a baseline system provided by the task organizers by more than 13 BLEU points. Moreover, according to an evaluation on a set of carefully-designed examples, the multi-encoder architecture is able to generate more coherent translations.- Anthology ID:
- 2020.wmt-1.56
- Volume:
- Proceedings of the Fifth Conference on Machine Translation
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 456–461
- Language:
- URL:
- https://aclanthology.org/2020.wmt-1.56
- DOI:
- Cite (ACL):
- Calvin Bao, Yow-Ting Shiue, Chujun Song, Jie Li, and Marine Carpuat. 2020. The University of Maryland’s Submissions to the WMT20 Chat Translation Task: Searching for More Data to Adapt Discourse-Aware Neural Machine Translation. In Proceedings of the Fifth Conference on Machine Translation, pages 456–461, Online. Association for Computational Linguistics.
- Cite (Informal):
- The University of Maryland’s Submissions to the WMT20 Chat Translation Task: Searching for More Data to Adapt Discourse-Aware Neural Machine Translation (Bao et al., WMT 2020)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2020.wmt-1.56.pdf