Abstract
Recent years have seen big advances in the field of sentence-level quality estimation (QE), largely as a result of using neural-based architectures. However, the majority of these methods work only on the language pair they are trained on and need retraining for new language pairs. This process can prove difficult from a technical point of view and is usually computationally expensive. In this paper we propose a simple QE framework based on cross-lingual transformers, and we use it to implement and evaluate two different neural architectures. Our evaluation shows that the proposed methods achieve state-of-the-art results outperforming current open-source quality estimation frameworks when trained on datasets from WMT. In addition, the framework proves very useful in transfer learning settings, especially when dealing with low-resourced languages, allowing us to obtain very competitive results.- Anthology ID:
- 2020.coling-main.445
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Editors:
- Donia Scott, Nuria Bel, Chengqing Zong
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 5070–5081
- Language:
- URL:
- https://aclanthology.org/2020.coling-main.445
- DOI:
- 10.18653/v1/2020.coling-main.445
- Cite (ACL):
- Tharindu Ranasinghe, Constantin Orasan, and Ruslan Mitkov. 2020. TransQuest: Translation Quality Estimation with Cross-lingual Transformers. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5070–5081, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Cite (Informal):
- TransQuest: Translation Quality Estimation with Cross-lingual Transformers (Ranasinghe et al., COLING 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.445.pdf
- Code
- tharindudr/transQuest