Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality?
Pei Zhang, Baosong Yang, Hao-Ran Wei, Dayiheng Liu, Kai Fan, Luo Si, Jun Xie
Abstract
Neural machine translation (NMT) is often criticized for failures that happenwithout awareness. The lack of competency awareness makes NMT untrustworthy. This is in sharp contrast to human translators who give feedback or conduct further investigations whenever they are in doubt about predictions. To fill this gap, we propose a novel competency-aware NMT by extending conventional NMT with a self-estimator, offering abilities to translate a source sentence and estimate its competency.The self-estimator encodes the information of the decoding procedure and then examines whether it can reconstruct the original semantics of the source sentence. Experimental results on four translation tasks demonstrate that the proposed method not only carries out translation tasks intact but also delivers outstanding performance on quality estimation.Without depending on any reference or annotated data typically required by state-of-the-art metric and quality estimation methods, our model yields an even higher correlation with human quality judgments than a variety of aforementioned methods, such as BLEURT, COMET, and BERTScore. Quantitative and qualitative analyses show better robustness of competency awareness in our model.- Anthology ID:
- 2022.emnlp-main.330
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4959–4970
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.330
- DOI:
- Cite (ACL):
- Pei Zhang, Baosong Yang, Hao-Ran Wei, Dayiheng Liu, Kai Fan, Luo Si, and Jun Xie. 2022. Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality?. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4959–4970, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality? (Zhang et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.emnlp-main.330.pdf