让印度语翻译模型更自然，21种语言对话翻译质量提升6.2分
Conversational Domain Adaptation of IndicTrans2 across 21 Indic Languages via Experience Replay and Model Soups
- 用经验回放和模型平均法，在不丢弃通用能力的前提下优化对话风格
- 21种印地语系语言对话效果平均提升6.2 chrF，通用任务性能几乎不变
- 首次在印地语族全语言规模上完成真实对话风格适配，适合多语言应用
IndicTrans2是当前最强的英译印地语系统，但其在日常对话场景中表现生硬。本文仅使用公开数据（OpenSubtitles、BPCC-H-Daily、Tatoeba），通过经验回放与模型平均（model soups）方法，将IndicTrans2-1B适配至21种印地语族语言的对话风格。单纯微调虽提升对话chrF，但通用领域性能下降3.9 chrF（FLORES Hindi测试）。引入经验回放并融合基线模型权重后，新模型在全部21种语言上对话chrF均超越原版（平均+6.2），且在FLORES上仅下降0.17（所有语言差值<0.7）。配对bootstrap检验确认对话提升显著（p ≤ 0.004），通用性能未显著退化。尽管人类与多模型LLM盲测未验证感知质量提升，我们仍认为该改进主要体现为与参考文本的风格匹配度提高。技术本身非首创，贡献在于在印地语族对话场景下完成诚实、端到端的实证研究。
原文摘要 · Abstract (English)
IndicTrans2 is the strongest open English to Indic translation system, but like most systems it is trained on general text and tends to sound stiff on casual, conversational input. We adapt IndicTrans2-1B to conversational register across all 21 Indic languages using only public data (OpenSubtitles, BPCC-H-Daily, Tatoeba). Plain fine-tuning improves conversational chrF but forgets the general domain (it drops 3.9 chrF on FLORES for Hindi). Mixing general data back into training (experience replay) and then averaging the fine-tuned weights with the base (model souping) removes that trade-off: the resulting model beats IndicTrans2-1B on conversational chrF in every one of the 21 languages (mean +6.2) while matching it on FLORES (mean change -0.17, all within 0.7 chrF). Paired bootstrap tests confirm the conversational gains are significant (p <= 0.004) and that FLORES is not significantly degraded. We are deliberate about scope: these are chrF gains, and a blind human plus multi-model LLM check does not confirm them as a perceived quality improvement, so we treat the conversational gain as largely a register match to the references rather than proof of better translation. The techniques are not new; the contribution is the honest, end-to-end study in the Indic conversational setting.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。