Anveshana: A New Benchmark Dataset for Cross-Lingual Information Retrieval On English Queries and Sanskrit Documents

The study presents a comprehensive benchmark for retrieving Sanskrit documents using English queries, focusing on the chapters of the Srimadbhagavatam. It employs a tripartite approach: Direct Retrieval (DR), Translation-based Retrieval (DT), and Query Translation (QT), utilizing shared embedding spaces and advanced translation methods to enhance retrieval systems in a RAG framework. The study fine-tunes state-of-the-art models for Sanskrit's linguistic nuances, evaluating models such as BM25, REPLUG, mDPR, ColBERT, Contriever, and GPT-2. It adapts summarization techniques for Sanskrit documents to improve QA processing. Evaluation shows DT methods outperform DR and QT in handling the cross-lingual challenges of ancient texts, improving accessibility and understanding. A dataset of 3,400 English-Sanskrit query-document pairs underpins the study, aiming to preserve Sanskrit scriptures and share their philosophical importance widely. Our dataset is publicly available atthis https URL

@article{jagadeeshan2025_2505.19494,
  title={ Anveshana: A New Benchmark Dataset for Cross-Lingual Information Retrieval On English Queries and Sanskrit Documents },
  author={ Manoj Balaji Jagadeeshan and Prince Raj and Pawan Goyal },
  journal={arXiv preprint arXiv:2505.19494},
  year={ 2025 }
}