ACL Findings2025
DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation
Xinglin Lyu, Wei Tang, Yuang Li, Xiaofeng Zhao, Ming Zhu, Junhui Li, Yunfei Lu, Min Zhang, Daimeng Wei, Hao Yang, Min Zhang
Abstract
Document-level context is crucial for handling discourse challenges in text-to-text documentlevel machine translation (MT). Despite the increased discourse challenges introduced by noise from automatic speech recognition (ASR), the integration of document-level context in speech translation (ST) remains insufficiently explored. In this paper, we develop DoCIA, an online framework that enhances ST performance by incorporating document-level context. DoCIA decomposes the ST pipeline into four stages. Document-level context is integrated into the ASR refinement, MT, and MT refinement stages through auxiliary LLM (large language model)-based modules. Furthermore, DoCIA leverages document-level information in a multi-level manner while minimizing computational overhead. Additionally, a simple yet effective determination mechanism is introduced to prevent hallucinations from excessive refinement, ensuring the reliability of the final results. Experimental results show that DoCIA significantly outperforms traditional ST baselines in both sentence and discourse metrics across four LLMs, demonstrating its effectiveness in improving ST performance. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts cites Generative Agents: Interactive Simulacra of Human Behavior
- Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate cites Generative Agents: Interactive Simulacra of Human Behavior
Cited by top-tier papers1
Builds on20
- Robust Speech Recognition via Large-Scale Weak SupervisionAlec Radford, Jong Wook Kim, Tao Xu, Greg Brockman et al.ICML 2023 · 6,966 citations
- CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model SocietyGuohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin et al.NeurIPS 2023 · 1,975 citations
- Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations
- Encouraging Divergent Thinking in Large Language Models through Multi-Agent DebateTian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang et al.EMNLP 2024 · 177 citations
- A Human-Inspired Reading Agent with Gist Memory of Very Long ContextsKuang-Huei Lee, Xinyun Chen, Hiroki Furuta, John F. Canny et al.ICML 2024 · 106 citations
Related papers
- SubDocTrans: Enhancing Document-level Machine Translation with Plug-and-play Multi-granularity Knowledge AugmentationHanghai Hong, Yibo Xie, Jiawei Zheng, Xiaoli WangEMNLP Findings 2025
- Exploring Discourse Structure in Document-level Machine TranslationXinyu Hu, Xiaojun WanEMNLP 2023 · 3 citations
- Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation RefinementYichen Dong, Xinglin Lyu, Junhui Li, Daimeng Wei et al.ACL 2025
- Document-Level Machine Translation with Large Language ModelsLongyue Wang, Chenyang Lyu, Tianbo Ji, Zhirui Zhang et al.EMNLP 2023 · 129 citations
- Exploring Context Strategies in LLMs for Discourse-Aware Machine TranslationRitvik Choudhary, Rem Hida, Masaki Hamada, Hayato Futami et al.EMNLP Findings 2025 · 1 citation
