Abstract
Simultaneous machine translation (SiMT) starts its translation before reading the whole source sentence and employs either fixed or adaptive policy to generate the target sentence. Compared to the fixed policy, the adaptive policy achieves better latency-quality tradeoffs by adopting a flexible translation policy. If the policy can evaluate rationality before taking action, the probability of incorrect actions will also decrease. However, previous methods lack evaluation of actions before taking them. In this paper, we propose a method of performing the adaptive policy via integrating post-evaluation into the fixed policy. Specifically, whenever a candidate token is generated, our model will evaluate the rationality of the next action by measuring the change in the source content. Our model will then take different actions based on the evaluation results. Experiments on three translation tasks show that our method can exceed strong baselines under all latency.- Anthology ID:
- 2022.findings-emnlp.167
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2022
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2264–2278
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.167
- DOI:
- 10.18653/v1/2022.findings-emnlp.167
- Cite (ACL):
- Shoutao Guo, Shaolei Zhang, and Yang Feng. 2022. Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2264–2278, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation (Guo et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2022.findings-emnlp.167.pdf