{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:07:30Z","timestamp":1784138850410,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809920","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"4305-4310","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ColBERTSaR: Sparsified ColBERT Index via Product Quantization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0051-1535","authenticated-orcid":false,"given":"Eugene","family":"Yang","sequence":"first","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5970-880X","authenticated-orcid":false,"given":"Andrew","family":"Yates","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7347-7086","authenticated-orcid":false,"given":"Dawn","family":"Lawrie","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3866-3013","authenticated-orcid":false,"given":"James","family":"Mayfield","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1827-2023","authenticated-orcid":false,"given":"Saron","family":"Samuel","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5008-4949","authenticated-orcid":false,"given":"Rohan","family":"Jha","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Machine Learning. PMLR, 929-947","author":"Armacki Aleksandar","year":"2022","unstructured":"Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic, and Soummya Kar. 2022. Gradient based clustering. In International Conference on Machine Learning. PMLR, 929-947."},{"key":"e_1_3_2_1_2_1","volume-title":"Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources. arXiv preprint arXiv:2407.20750","author":"Clavi\u00e9 Benjamin","year":"2024","unstructured":"Benjamin Clavi\u00e9. 2024. JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources. arXiv preprint arXiv:2407.20750 (2024)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1572114"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657968"},{"key":"e_1_3_2_1_5_1","volume-title":"SPLADE v2: Sparse lexical and expansion model for information retrieval. arXiv preprint arXiv:2109.10086","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, Carlos Lassance, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021a. SPLADE v2: Sparse lexical and expansion model for information retrieval. arXiv preprint arXiv:2109.10086 (2021)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463098"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72240-1_23"},{"key":"e_1_3_2_1_8_1","volume-title":"Optimized product quantization","author":"Ge Tiezheng","year":"2013","unstructured":"Tiezheng Ge, Kaiming He, Qifa Ke, and Jian Sun. 2013. Optimized product quantization. IEEE transactions on pattern analysis and machine intelligence, Vol. 36, 4 (2013), 744-755."},{"key":"e_1_3_2_1_9_1","volume-title":"Ravishankar Krishnawamy, and Rohan Kadekodi.","author":"Subramanya Suhas Jayaram","year":"2019","unstructured":"Suhas Jayaram Subramanya, Fnu Devvrit, Harsha Vardhan Simhadri, Ravishankar Krishnawamy, and Rohan Kadekodi. 2019. Diskann: Fast accurate billion-point nearest neighbor search on a single node. Advances in neural information processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_11_1","volume-title":"Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick SH Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering.. In EMNLP (1). 6769-6781."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_13_1","volume-title":"SPLADE-v3: New baselines for SPLADE. arXiv preprint arXiv:2403.06789","author":"Lassance Carlos","year":"2024","unstructured":"Carlos Lassance, Herv\u00e9 D\u00e9jean, Thibault Formal, and St\u00e9phane Clinchant. 2024. SPLADE-v3: New baselines for SPLADE. arXiv preprint arXiv:2403.06789 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"NeuCLIRTech: Chinese Monolingual and Cross-Language Information Retrieval Evaluation in a Challenging Domain. arXiv preprint arXiv:2602.05334","author":"Lawrie Dawn","year":"2026","unstructured":"Dawn Lawrie, James Mayfield, Eugene Yang, Andrew Yates, Sean MacAvaney, Ronak Pradeep, Scott Miller, Paul McNamee, and Luca Soldaini. 2026. NeuCLIRTech: Chinese Monolingual and Cross-Language Information Retrieval Evaluation in a Challenging Domain. arXiv preprint arXiv:2602.05334 (2026)."},{"key":"e_1_3_2_1_15_1","volume-title":"Cross-Language, and Multilingual Information Retrieval. arXiv preprint arXiv:2511.14758","author":"Lawrie Dawn","year":"2025","unstructured":"Dawn Lawrie, James Mayfield, Eugene Yang, Andrew Yates, Sean MacAvaney, Ronak Pradeep, Scott Miller, Paul McNamee, and Luca Soldani. 2025. NeuCLIRBench: A Modern Evaluation Collection for Monolingual, Cross-Language, and Multilingual Information Retrieval. arXiv preprint arXiv:2511.14758 (2025)."},{"key":"e_1_3_2_1_16_1","volume-title":"Tao Lei, Iftekhar Naim, Ming-Wei Chang, and Vincent Zhao.","author":"Lee Jinhyuk","year":"2024","unstructured":"Jinhyuk Lee, Zhuyun Dai, Sai Meher Karthik Duddu, Tao Lei, Iftekhar Naim, Ming-Wei Chang, and Vincent Zhao. 2024. Rethinking the role of token retrieval in multi-vector retrieval. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.663"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657856"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.205"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463030"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56060-6_1"},{"key":"e_1_3_2_1_22_1","volume-title":"Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector. arXiv preprint arXiv:2510.00671","author":"Nguyen Thong","year":"2025","unstructured":"Thong Nguyen, Yibin Lei, Jia-Huei Ju, Eugene Yang, and Andrew Yates. 2025. Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector. arXiv preprint arXiv:2510.00671 (2025)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28241-6_7"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557325"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729904"},{"key":"e_1_3_2_1_27_1","volume-title":"Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663 (2021)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591916"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657955"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56060-6_4"},{"key":"e_1_3_2_1_31_1","volume-title":"Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176","author":"Zhang Yanzhao","year":"2025","unstructured":"Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, et al., 2025. Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176 (2025)."}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:19:19Z","timestamp":1784135959000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809920"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":31,"alternative-id":["10.1145\/3805712.3809920","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809920","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}