Adversarially Improving NMT Robustness to ASR Errors with Confusion Sets
Shuaibo Wang, Yufeng Chen, Songming Zhang, Deyi Xiong, Jinan Xu
Abstract
Neural machine translation (NMT) models are known to be fragile to noisy inputs from automatic speech recognition (ASR) systems. Existing methods are usually tailored for robustness against only homophone errors which account for a small portion of realistic ASR errors. In this paper, we propose an adversarial example generation method based on confusion sets that contain words easily confusable with a target word by ASR to conduct adversarial training for NMT models. Specifically, an adversarial example is generated from the perspective of acoustic relations instead of the traditional uniform or unigram sampling from the confusion sets. Experiments on different test sets with hand-crafted and real-world noise demonstrate the effectiveness of our method over previous methods. Moreover, our approach can achieve improvements on the clean test set.- Anthology ID:
- 2022.aacl-short.28
- Volume:
- Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
- Month:
- November
- Year:
- 2022
- Address:
- Online only
- Venues:
- AACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 221–227
- Language:
- URL:
- https://aclanthology.org/2022.aacl-short.28
- DOI:
- Cite (ACL):
- Shuaibo Wang, Yufeng Chen, Songming Zhang, Deyi Xiong, and Jinan Xu. 2022. Adversarially Improving NMT Robustness to ASR Errors with Confusion Sets. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 221–227, Online only. Association for Computational Linguistics.
- Cite (Informal):
- Adversarially Improving NMT Robustness to ASR Errors with Confusion Sets (Wang et al., AACL-IJCNLP 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.aacl-short.28.pdf