The University of Edinburgh-Uppsala University’s Submission to the WMT 2020 Chat Translation Task
| Autor: | Nikita Moghe, Christian Hardmeier, Rachel Bawden |
|---|---|
| Přispěvatelé: | School of Informatics [Edimbourg], University of Edinburgh, Department of Linguistics and Philology, Uppsala University |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: | |
| Zdroj: | Proceedings of the 5th Conference on Machine Translation 5th Conference on Machine Translation 5th Conference on Machine Translation, Nov 2020, Online, Unknown Region Moghe, N, Hardmeier, C & Bawden, R 2020, The University of Edinburgh-Uppsala University’s Submission to the WMT 2020 Chat Translation Task . in Proceedings of the Fifth Conference on Machine Translation . pp. 473-478, Fifth Conference on Machine Translation, Online Conference, 19/11/20 . < https://www.aclweb.org/anthology/2020.wmt-1.58 > HAL |
| Popis: | International audience; This paper describes the joint submission of the University of Edinburgh and Uppsala University to the WMT'20 chat translation task for both language directions (English↔German). We use existing state-of-the-art machine translation models trained on news data and fine-tune them on in-domain and pseudo-in-domain web crawled data. We also experiment with (i) adaptation using speaker and domain tags and (ii) using different types and amounts of preceding context. We observe that contrarily to expectations, exploiting context degrades the results (and on analysis the data is not highly contextual). However using domain tags does improve scores according to the automatic evaluation. Our final primary systems use domain tags and are ensembles of 4 models, with noisy channel reranking of outputs. Our en-de system was ranked second in the shared task while our de-en system outperformed all the other systems. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|