@inproceedings{acharya-etal-2025-benchmarking,
    title = "Benchmarking and Building Zero-Shot {H}indi Retrieval Model with {H}indi-{BEIR} and {NLLB}-E5",
    author = "Acharya, Arkadeep  and
      Murthy, Rudra  and
      Kumar, Vishwajeet  and
      Sen, Jaydeep",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-long.220/",
    pages = "4328--4348",
    ISBN = "979-8-89176-189-6",
    abstract = "Given the large number of Hindi speakers worldwide, there is a pressing need for robust and efficient information retrieval systems for Hindi. Despite ongoing research, comprehensive benchmarks for evaluating retrieval models in Hindi are lacking. To address this gap, we introduce the Hindi-BEIR benchmark, comprising 15 datasets across seven distinct tasks. We evaluate state-of-the-art multilingual retrieval models on the Hindi-BEIR benchmark, identifying task and domain-specific challenges that impact Hindi retrieval performance. Building on the insights from these results, we introduce NLLB-E5, a multilingual retrieval model that leverages a zero-shot approach to support Hindi without the need for Hindi training data. We believe our contributions, including the release of the Hindi-BEIR benchmark and the NLLB-E5 model, will be a valuable resource for researchers and promote advancements in multilingual retrieval models."
}