Title | ||
---|---|---|
The University of Maryland's Submissions to the WMT20 Chat Translation Task - Searching for More Data to Adapt Discourse-Aware Neural Machine Translation. |
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. |
Year | Venue | DocType |
---|---|---|
2020 | WMT@EMNLP | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Calvin Bao | 1 | 0 | 0.34 |
Yow-Ting Shiue | 2 | 0 | 2.03 |
Chujun Song | 3 | 0 | 0.34 |
Jie Li | 4 | 300 | 62.08 |
Marine Carpuat | 5 | 587 | 51.99 |