English-Czech Systems in WMT19: Document-Level Transformer
Martin Popel, Dominik Macháček, Michal Auersperger, Ondřej Bojar, Pavel Pecina
Abstract
We describe our NMT systems submitted to the WMT19 shared task in English→Czech news translation. Our systems are based on the Transformer model implemented in either Tensor2Tensor (T2T) or Marian framework. We aimed at improving the adequacy and coherence of translated documents by enlarging the context of the source and target. Instead of translating each sentence independently, we split the document into possibly overlapping multi-sentence segments. In case of the T2T implementation, this “document-level”-trained system achieves a +0.6 BLEU improvement (p < 0.05) relative to the same system applied on isolated sentences. To assess the potential effect document-level models might have on lexical coherence, we performed a semi-automatic analysis, which revealed only a few sentences improved in this aspect. Thus, we cannot draw any conclusions from this week evidence.- Anthology ID:
- W19-5337
- Volume:
- Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 342–348
- Language:
- URL:
- https://aclanthology.org/W19-5337
- DOI:
- 10.18653/v1/W19-5337
- Cite (ACL):
- Martin Popel, Dominik Macháček, Michal Auersperger, Ondřej Bojar, and Pavel Pecina. 2019. English-Czech Systems in WMT19: Document-Level Transformer. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 342–348, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- English-Czech Systems in WMT19: Document-Level Transformer (Popel et al., WMT 2019)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/W19-5337.pdf