Neural Lexical Search with Learned Sparse Retrieval
Learned Sparse Retrieval (LSR) techniques use neural machinery to represent queries and documents as learned bags of words. In contrast with other neural retrieval techniques, such as generative retrieval and dense retrieval, LSR has been shown to be a remarkably robust, transferable, and efficient family of methods for retrieving high-quality search results. This half-day tutorial aims to provide an extensive overview of LSR, ranging from its fundamentals to the latest emerging techniques. By the end of the tutorial, attendees will be familiar with the important design decisions of an LSR system, know how to apply them to text and other modalities, and understand the latest techniques for retrieving with them efficiently. Website: https://lsr-tutorial.github.io
Authors
- Sean MacAvaney (ORCID: https://orcid.org/0000-0002-8914-2659)
- Cosimo Rulli (ORCID: https://orcid.org/0000-0003-0194-361X)
- Andrew Yates (ORCID: https://orcid.org/0000-0002-5970-880X)
- Eugene Yang (ORCID: https://orcid.org/0000-0002-0051-1535)
- Carlos Lassance (ORCID: https://orcid.org/0000-0002-7754-6656)
- Yibin Lei (ORCID: https://orcid.org/0009-0007-9558-5548)
- Thong Nguyen (ORCID: https://orcid.org/0000-0003-0607-0723)
- Satendra Singh (ORCID: https://orcid.org/0009-0009-8835-5845)
Institutions
- Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo" (IT)
- Johns Hopkins University (US)
- Amsterdam University of the Arts (NL)
- University of Glasgow (GB)
- University of Amsterdam (NL)
Publication Details
- Published
- 2025-07-13
- DOI
- https://doi.org/10.1145/3726302.3731693
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Nederlandse Organisatie voor Wetenschappelijk Onderzoek