用检索增强生成技术，让小模型也能高效翻译孟加拉语方言。
A Comparative Analysis of Retrieval-Augmented Generation Techniques for Bengali Standard-to-Dialect Machine Translation Using LLMs
- 设计两种检索增强管道，用结构化句对提升方言翻译效果。
- 在6种方言上，词错误率从76%降至55%，小模型超越大模型。
- 无需微调，适合资源匮乏的低资源语言翻译场景。
由于数据稀缺和语言差异，将标准语翻译为地区方言是自然语言处理中的重大挑战，尤其在孟加拉语中尤为突出。本文提出并比较了两种新颖的RAG管道用于标准到方言的孟加拉语翻译。第一种为基于转录文本的管道，利用音频转录中的大段方言句子上下文；第二种为更有效的标准化句对管道，使用结构化的本地方言:标准孟加拉语句对。我们在六个孟加拉语方言和多个大型语言模型上，采用BLEU、ChrF、WER和BERTScore进行评估。结果表明，句对管道始终优于转录管道，使吉大港方言的词错误率（WER）从76%降低至55%。关键发现是，这种RAG方法使较小模型（如Llama-3.1-8B）的表现超过更大模型（如GPT-OSS-120B），证明精心设计的检索策略比模型规模更重要。本工作提供了一种无需微调的高效解决方案，适用于低资源方言翻译，为保护语言多样性提供了实用蓝图。
原文摘要 · Abstract (English)
Translating from a standard language to its regional dialects is a significant NLP challenge due to scarce data and linguistic variation, a problem prominent in the Bengali language. This paper proposes and compares two novel RAG pipelines for standard-to-dialectal Bengali translation. The first, a Transcript-Based Pipeline, uses large dialect sentence contexts from audio transcripts. The second, a more effective Standardized Sentence-Pairs Pipeline, utilizes structured local\_dialect:standard\_bengali sentence pairs. We evaluated both pipelines across six Bengali dialects and multiple LLMs using BLEU, ChrF, WER, and BERTScore. Our findings show that the sentence-pair pipeline consistently outperforms the transcript-based one, reducing Word Error Rate (WER) from 76\% to 55\% for the Chittagong dialect. Critically, this RAG approach enables smaller models (e.g., Llama-3.1-8B) to outperform much larger models (e.g., GPT-OSS-120B), demonstrating that a well-designed retrieval strategy can be more crucial than model size. This work contributes an effective, fine-tuning-free solution for low-resource dialect translation, offering a practical blueprint for preserving linguistic diversity.
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。