Abstract
Simultaneous Machine Translation (SiMT) requires target tokens to be generated in real-time as streaming source tokens are consumed. Traditional approaches to SiMT typically require sophisticated architectures and extensive parameter configurations for training adaptive read/write policies, which in turn demand considerable computational power and memory. We propose PsFuture, the first zero-shot adaptive read/write policy for SiMT, enabling the translation model to independently determine read/write actions without the necessity for additional training. Furthermore, we introduce a novel training strategy, Prefix-to-Full (P2F), specifically tailored to adjust offline translation models for SiMT applications, exploiting the advantages of the bidirectional attention mechanism inherent in offline models. Experiments across multiple benchmarks demonstrate that our zero-shot policy attains performance on par with strong baselines and the P2F method can further enhance performance, achieving an outstanding trade-off between translation quality and latency.- Anthology ID:
- 2024.emnlp-main.111
- Volume:
- Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1869–1881
- Language:
- URL:
- https://aclanthology.org/2024.emnlp-main.111
- DOI:
- 10.18653/v1/2024.emnlp-main.111
- Cite (ACL):
- Libo Zhao, Jing Li, and Ziqian Zeng. 2024. PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 1869–1881, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation (Zhao et al., EMNLP 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.emnlp-main.111.pdf