用多语言嵌入模型实现僧伽罗语和泰米尔语政府信息检索，效果优于翻译方法。
Query Translation vs. Cross-Lingual Embeddings for Sinhala-Tamil E-Government Information Retrieval
- 采用多语言嵌入模型直接匹配异构语言查询与英文文档
- BGE-M3在僧伽罗语-英语和泰米尔语-英语检索中达96.2%和95.6%的召回率
- 避免翻译开销，适合低资源政府场景下的RAG应用
本文对比评估了在斯里兰卡政府信息中心（GIC）提供的1,699段文本中生成的500组僧伽罗语、泰米尔语和英语问答对上，使用僧伽罗语和泰米尔语查询检索英文政府信息的跨语言信息检索（CLIR）方法。研究比较了两种范式：基于Google Translate、NLLB和mBART50的查询翻译（QT），以及使用LaBSE、multilingual E5和BGE-M3的跨语言嵌入（CLE）。以单语英文检索为基线，评估指标为Recall@k（k=1,3,5,10,15）。单语检索表现差（Recall@15 <10%），而所有CLIR方法均显著提升准确率。其中，BGE-M3在僧伽罗语-英语和泰米尔语-英语任务中分别达到96.2%和95.6%的Recall@15，优于最佳翻译方法（Google Translate：92.4%和93.0%），且无需翻译过程。结果表明，多语言嵌入模型在低资源政府领域跨语言检索增强生成（RAG）中更具有效性和可扩展性。
原文摘要 · Abstract (English)
This paper presents a comparative evaluation of cross-lingual information retrieval (CLIR) methods for retrieving English government information using Sinhala and Tamil queries. Two CLIR paradigms are investigated: Query Translation (QT), employing Google Translate, NLLB, and mBART50, and Cross-Lingual Embeddings (CLE), using LaBSE, multilingual E5, and BGE-M3, with monolingual English retrieval as the baseline. Experiments are conducted on a human-verified benchmark comprising 500 Sinhala, Tamil, and English question-answer pairs derived from 1,699 segmented contexts from Sri Lanka's Government Information Center (GIC). Retrieval performance is evaluated using Recall@k (k = 1, 3, 5, 10, 15). Monolingual retrieval performs poorly (Recall@15 <10%), whereas all CLIR approaches substantially improve retrieval accuracy. Among them, BGE-M3 achieves the highest Recall@15, reaching 96.2% for Sinhala-English and 95.6% for Tamil-English, outperforming the best QT approach (Google Translate: 92.4% and 93.0%) while avoiding translation overhead. These results demonstrate that multilingual embedding models provide a more effective and scalable solution for cross-lingual retrieval-augmented generation (RAG) in low-resource government domains.
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。