用翻译流水线+小模型实现多语言对话高效处理
Efficient Multilingual Dialogue Processing via Translation Pipelines and Distilled Language Models
- 三阶段流水线：印地语转英文，小模型生成，再译回源语言
- 9种语言中，马拉地语、泰米尔语问答准确率达86.7%，印地语达80.0%
- 无需任务微调，适合低资源语言的快速部署
本文介绍团队Kl33n3x为NLPAI4Health 2025共享任务开发的多语言对话摘要与问答系统。该方法采用三阶段流水线：将印地语系语言正向翻译至英文，利用参数量为2.55B的蒸馏语言模型进行多任务文本生成，再反向翻译回源语言。通过知识蒸馏技术，本研究证明紧凑模型可在九种语言上实现极具竞争力的表现。系统在竞赛各项任务中取得优异胜率，尤其在马拉地语（86.7% QnA）、泰米尔语（86.7% QnA）和印地语（80.0% QnA）上表现稳健，验证了基于翻译的方法在无任务特定微调情况下处理低资源语言的有效性。
原文摘要 · Abstract (English)
This paper presents team Kl33n3x's multilingual dialogue summarization and question answering system developed for the NLPAI4Health 2025 shared task. The approach employs a three-stage pipeline: forward translation from Indic languages to English, multitask text generation using a 2.55B parameter distilled language model, and reverse translation back to source languages. By leveraging knowledge distillation techniques, this work demonstrates that compact models can achieve highly competitive performance across nine languages. The system achieved strong win rates across the competition's tasks, with particularly robust performance on Marathi (86.7% QnA), Tamil (86.7% QnA), and Hindi (80.0% QnA), demonstrating the effectiveness of translation-based approaches for low-resource language processing without task-specific fine-tuning.
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。