Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies

Qianen Zhang, Zeyu Yang, Satoshi Nakamura


Abstract
Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional policies with only READ/WRITE actions cannot fully address. We extend the action space of SiMT with four adaptive actions: Sentence_Cut, Drop, Partial_Summarization and Pronominalization, which enable real-time restructuring, omission, and simplification while preserving semantic fidelity. We adapt these actions in a large language model (LLM) framework and construct training references through action-aware prompting. To evaluate both quality and word-level monotonicity, we further develop a latency-aware TTS pipeline that maps textual outputs to speech with realistic timing. Experiments on the ACL60/60 English-Chinese, English-German and English-Japanese benchmarks show that our framework consistently improves semantic metrics and achieves lower delay compared to reference translations and salami-based baselines. Notably, combining Drop and Sentence_Cut leads to consistent improvements in the balance between fluency and latency. These results demonstrate that enriching the action space of LLM-based SiMT provides a promising direction for bridging the gap between human and machine interpretation.
Anthology ID:
2026.iwslt-1.2
Volume:
Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)
Month:
July
Year:
2026
Address:
San Diego, USA (in-person and online)
Editors:
Elizabeth Salesky, Antonios Anastasopoulos, Matteo Negri, Marcello Federico
Venues:
IWSLT | WS
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
8–31
Language:
URL:
https://aclanthology.org/2026.iwslt-1.2/
DOI:
Bibkey:
Cite (ACL):
Qianen Zhang, Zeyu Yang, and Satoshi Nakamura. 2026. Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies. In Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026), pages 8–31, San Diego, USA (in-person and online). Association for Computational Linguistics.
Cite (Informal):
Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies (Zhang et al., IWSLT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.iwslt-1.2.pdf