{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:29:58Z","timestamp":1783736998374,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["IIS-2225942"],"award-info":[{"award-number":["IIS-2225942"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657972","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"2327-2331","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Cluster-based Partial Dense Retrieval Fused with Sparse Text Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6454-5796","authenticated-orcid":false,"given":"Yingrui","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of California, Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-5088","authenticated-orcid":false,"given":"Parker","family":"Carlson","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of California, Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8581-6733","authenticated-orcid":false,"given":"Shanxiu","family":"He","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of California, Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5717-2637","authenticated-orcid":false,"given":"Yifan","family":"Qiao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of California, Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1902-3387","authenticated-orcid":false,"given":"Tao","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of California at Santa Barbara, Santa Barbara, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Lin (Eds.)","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877--1901."},{"key":"e_1_3_2_1_2_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. NIPS","author":"Campos Daniel Fernando","year":"2016","unstructured":"Daniel Fernando Campos, Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, Li Deng, and Bhaskar Mitra. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. NIPS (2016)."},{"key":"e_1_3_2_1_3_1","volume-title":"SPANN: Highly-efficient Billion-scale Approximate Nearest Neighborhood Search. In Advances in Neural Information Processing Systems","author":"Chen Qi","year":"2021","unstructured":"Qi Chen, Bing Zhao, Haidong Wang, Mingqin Li, Chuanjie Liu, Zengzhong Li, Mao Yang, and Jingdong Wang. 2021. SPANN: Highly-efficient Billion-scale Approximate Nearest Neighborhood Search. In Advances in Neural Information Processing Systems, A. Beygelzimer, Y. Dauphin, P. Liang, and J.Wortman Vaughan (Eds.)."},{"key":"e_1_3_2_1_4_1","volume-title":"Overview of the TREC 2020 Deep Learning Track. ArXiv abs\/2102","author":"Craswell Nick","year":"2020","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Fernando Campos, and Ellen M. Voorhees. 2020. Overview of the TREC 2020 Deep Learning Track. ArXiv abs\/2102.07662 (2020)."},{"key":"e_1_3_2_1_5_1","volume-title":"Context-Aware Term Weighting For First Stage Passage Retrieval. SIGIR","author":"Dai Zhuyun","year":"2020","unstructured":"Zhuyun Dai and Jamie Callan. 2020. Context-Aware Term Weighting For First Stage Passage Retrieval. SIGIR (2020)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531857"},{"key":"e_1_3_2_1_7_1","volume-title":"SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. SIGIR","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021. SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. SIGIR (2021)."},{"key":"e_1_3_2_1_8_1","volume-title":"COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List. NAACL","author":"Gao Luyu","year":"2021","unstructured":"Luyu Gao, Zhuyun Dai, and Jamie Callan. 2021. COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List. NAACL (2021)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Luyu Gao Zhuyun Dai Zhen Fan and J. Callan. 2021. Complementing Lexical Retrieval with Semantic Residual Embedding. ECIR abs\/2004.13969 (2021).","DOI":"10.1007\/978-3-030-72113-8_10"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583552"},{"key":"e_1_3_2_1_11_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. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_13_1","volume-title":"Dense Passage Retrieval for Open-Domain Question Answering. EMNLP'2020 ArXiv abs\/2010","author":"Karpukhin V.","year":"2020","unstructured":"V. Karpukhin, Barlas O\u011fuz, Sewon Min, Patrick Lewis, Ledell Yu Wu, Sergey Edunov, Danqi Chen, and Wen tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. EMNLP'2020 ArXiv abs\/2010.08191 (2020)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591715"},{"key":"e_1_3_2_1_15_1","volume-title":"Leveraging semantic and lexical matching to improve the recall of document retrieval systems: A hybrid approach. arXiv preprint arXiv:2010.01195","author":"Kuzi Saar","year":"2020","unstructured":"Saar Kuzi, Mingyang Zhang, Cheng Li, Michael Bendersky, and Marc Najork. 2020. Leveraging semantic and lexical matching to improve the recall of document retrieval systems: A hybrid approach. arXiv preprint arXiv:2010.01195 (2020)."},{"key":"e_1_3_2_1_16_1","volume-title":"An Efficiency Study for SPLADE Models. SIGIR","author":"Lassance Carlos","year":"2022","unstructured":"Carlos Lassance and St\u00e9phane Clinchant. 2022. An Efficiency Study for SPLADE Models. SIGIR (2022)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591941"},{"key":"e_1_3_2_1_18_1","volume-title":"Interpolate: PRF, Dense and Sparse Retrievers. SIGIR","author":"Li Hang","year":"2022","unstructured":"Hang Li, Shuai Wang, Shengyao Zhuang, Ahmed Mourad, Xueguang Ma, Jimmy Lin, and G. Zuccon. 2022. To Interpolate or not to Interpolate: PRF, Dense and Sparse Retrievers. SIGIR (2022)."},{"key":"e_1_3_2_1_19_1","volume-title":"Lin and Xueguang Ma","author":"Jimmy","year":"2021","unstructured":"Jimmy J. Lin and Xueguang Ma. 2021. A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques. ArXiv abs\/2106.14807 (2021)."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Anna Rogers, Jordan Boyd-Graber","author":"Liu Zheng","unstructured":"Zheng Liu, Shitao Xiao, Yingxia Shao, and Zhao Cao. 2023. RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki (Eds.). Association for Computational Linguistics, Toronto, Canada, 2635--2648."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"e_1_3_2_1_22_1","unstructured":"Xueguang Ma Liang Wang Nan Yang Furu Wei and Jimmy Lin. 2023. Fine-Tuning LLaMA for Multi-Stage Text Retrieval. arXiv:2310.08319 [cs.IR]"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557231"},{"key":"e_1_3_2_1_24_1","volume-title":"Accelerating Learned Sparse Indexes Via Term Impact Decomposition. In Findings of the Association for Computational Linguistics: EMNLP","author":"Mackenzie Joel","year":"2022","unstructured":"Joel Mackenzie, Antonio Mallia, Alistair Moffat, and Matthias Petri. 2022. Accelerating Learned Sparse Indexes Via Term Impact Decomposition. In Findings of the Association for Computational Linguistics: EMNLP 2022, Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang (Eds.). ACL, Abu Dhabi, United Arab Emirates, 2830--2842."},{"key":"e_1_3_2_1_25_1","article-title":"Anytime Ranking on Document-Ordered Indexes","volume":"40","author":"Mackenzie Joel","year":"2021","unstructured":"Joel Mackenzie, Matthias Petri, and Alistair Moffat. 2021. Anytime Ranking on Document-Ordered Indexes. ACM Trans. Inf. Syst. 40, 1, Article 13 (sep 2021), 32 pages.","journal-title":"ACM Trans. Inf. Syst."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_1_27_1","volume-title":"Learning Passage Impacts for Inverted Indexes. SIGIR","author":"Mallia Antonio","year":"2021","unstructured":"Antonio Mallia, O. Khattab, Nicola Tonellotto, and Torsten Suel. 2021. Learning Passage Impacts for Inverted Indexes. SIGIR (2021)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531774"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the Open-Source IR Replicability Challenge","author":"Mallia Antonio","year":"2019","unstructured":"Antonio Mallia, Michal Siedlaczek, Joel Mackenzie, and Torsten Suel. 2019. PISA: Performant indexes and search for academia. Proceedings of the Open-Source IR Replicability Challenge (2019)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730881"},{"key":"e_1_3_2_1_31_1","volume-title":"Representation Sparsification with Hybrid Thresholding for Fast SPLADE-based Document Retrieval. ACM SIGIR'23","author":"Qiao Yifan","year":"2023","unstructured":"Yifan Qiao, Yingrui Yang, Shanxiu He, and Tao Yang. 2023. Representation Sparsification with Hybrid Thresholding for Fast SPLADE-based Document Retrieval. ACM SIGIR'23 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583497"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_34_1","volume-title":"LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PfpEtB3-csK","author":"Shen Tao","year":"2023","unstructured":"Tao Shen, Xiubo Geng, Chongyang Tao, Can Xu, Xiaolong Huang, Binxing Jiao, Linjun Yang, and Daxin Jiang. 2023. LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PfpEtB3-csK"},{"key":"e_1_3_2_1_35_1","volume-title":"TextMining Workshop at KDD2000","author":"Steinbach Michael","year":"2000","unstructured":"Michael Steinbach, George Karypis, and Vipin Kumar. 2000. A comparison of document clustering techniques. TextMining Workshop at KDD2000 (2000)."},{"key":"e_1_3_2_1_36_1","volume-title":"BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In NeurIPS.","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In NeurIPS."},{"key":"e_1_3_2_1_37_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv:2307.09288 [cs.CL]"},{"key":"e_1_3_2_1_38_1","volume-title":"Order Statistic. https:\/\/en.wikipedia.org\/wiki\/Order_statistic","year":"2023","unstructured":"Wikipedia. 2023. Order Statistic. https:\/\/en.wikipedia.org\/wiki\/Order_statistic (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531799"},{"key":"e_1_3_2_1_40_1","volume-title":"RetroMAE: Pretraining Retrieval-oriented Transformers via Masked Auto-Encoder. EMNLP","author":"Xiao Shitao","year":"2022","unstructured":"Shitao Xiao, Zheng Liu, Yingxia Shao, and Zhao Cao. 2022. RetroMAE: Pretraining Retrieval-oriented Transformers via Masked Auto-Encoder. EMNLP (2022)."},{"key":"e_1_3_2_1_41_1","volume-title":"Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance. CIKM","author":"Zhan Jingtao","year":"2021","unstructured":"Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, and Shaoping Ma. 2021. Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance. CIKM (2021)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498443"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657972","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657972","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:18:40Z","timestamp":1755839920000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657972"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":42,"alternative-id":["10.1145\/3626772.3657972","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657972","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}