Search papers, labs, and topics across Lattice.
This paper evaluates the effectiveness of two cross-lingual information retrieval (CLIR) methods—Query Translation (QT) and Cross-Lingual Embeddings (CLE)—for retrieving English government information using Sinhala and Tamil queries. The study utilizes a benchmark of 500 human-verified question-answer pairs and finds that while monolingual retrieval is ineffective, CLE methods, particularly BGE-M3, significantly enhance retrieval accuracy, achieving Recall@15 rates of 96.2% for Sinhala-English and 95.6% for Tamil-English. The findings indicate that multilingual embedding models offer a superior and scalable alternative for cross-lingual retrieval in low-resource contexts compared to traditional translation methods.
Multilingual embeddings can boost cross-lingual retrieval accuracy to over 96%, far surpassing traditional translation methods.
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.
