Abstract
In this paper, we describe the submissions of the team from Nanjing University for the WMT19 sentence-level Quality Estimation (QE) shared task on English-German language pair. We develop two approaches based on a two-stage neural QE model consisting of a feature extractor and a quality estimator. More specifically, one of the proposed approaches employs the translation knowledge between the two languages from two different translation directions; while the other one employs extra monolingual knowledge from both source and target sides, obtained by pre-training deep self-attention networks. To efficiently train these two-stage models, a joint learning training method is applied. Experiments show that the ensemble model of the above two models achieves the best results on the benchmark dataset of the WMT17 sentence-level QE shared task and obtains competitive results in WMT19, ranking 3rd out of 10 submissions.- Anthology ID:
- W19-5409
- Volume:
- Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 95–100
- Language:
- URL:
- https://aclanthology.org/W19-5409
- DOI:
- 10.18653/v1/W19-5409
- Cite (ACL):
- Hou Qi. 2019. NJU Submissions for the WMT19 Quality Estimation Shared Task. In Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), pages 95–100, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- NJU Submissions for the WMT19 Quality Estimation Shared Task (Qi, WMT 2019)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/W19-5409.pdf