# When to Use Extra Context: Evidence-Grounded Terminology Adaptation for Simultaneous Speech Translation

arXiv: https://arxiv.org/abs/2607.17766 · HTML: https://mlsanity.com/paper/2607.17766/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation](https://mlsanity.com/paper/1804.06609/) (2018)
- [Deep context: end-to-end contextual speech recognition](https://mlsanity.com/paper/1808.02480/) (2018)
- [SeamlessM4T: Massively Multilingual & Multimodal Machine Translation](https://mlsanity.com/paper/2308.11596/) (2023)
- [Direct speech-to-speech translation with a sequence-to-sequence model](https://mlsanity.com/paper/1904.06037/) (2019)
- [Monotonic Infinite Lookback Attention for Simultaneous Machine Translation](https://mlsanity.com/paper/1906.05218/) (2019)
- [Context-Aware Neural Machine Translation Learns Anaphora Resolution](https://mlsanity.com/paper/1805.10163/) (2018)
- [SimulEval: An Evaluation Toolkit for Simultaneous Translation](https://mlsanity.com/paper/2007.16193/) (2020)
- [Training Neural Machine Translation To Apply Terminology Constraints](https://mlsanity.com/paper/1906.01105/) (2019)
- [Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation](https://mlsanity.com/paper/2206.05807/) (2022)
- [Measuring and Increasing Context Usage in Context-Aware Machine Translation](https://mlsanity.com/paper/2105.03482/) (2021)
- [Information-Transport-based Policy for Simultaneous Translation](https://mlsanity.com/paper/2210.12357/) (2022)
- [MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks](https://mlsanity.com/paper/2507.19634/) (2025)

## Abstract (arXiv)

Extra context is valuable for simultaneous speech translation of technical talks, but injecting the entire document context into every streaming segment is often too coarse. Through diagnostic experiments, we find that context gains mainly come from paper-specific terminology recovery rather than uniform semantic enhancement. We therefore propose EGTA, an Evidence-Grounded Terminology Adaptation framework that builds a document terminology memory, selects compact candidate terms conditioned on the current streaming state, and adapts ASR/speech-side and decoder-side decision spaces using only the selected terms. EGTA can be instantiated in cascaded, end-to-end, and generation-only SimulST settings without full-model fine-tuning. We evaluate EGTA on an ACL technical-talk SimulST evaluation suite consisting of MCIF-dev and ACL60/60-dev. On MCIF-dev, EGTA-RG improves BLEU by +1.05/+0.59, XCOMET-XL by +0.019/+0.006, named-entity recall by +79%/+73% relative, and acronym recall by +0.099/+0.171 on EnrightarrowZh and EnrightarrowDe. Across MCIF-dev latency settings, EGTA consistently improves XCOMET-XL, named-entity recall, and acronym recall. External validation on ACL60/60-dev further shows consistent terminology-recall gains without additional fine-tuning. Shuffled-memory controls and activation audits provide evidence that the improvements are tied to paper-specific evidence alignment rather than generic context prompting.