{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T04:17:15Z","timestamp":1789705035501,"version":"4.0.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Tsinghua-Tencent Tiangong Institute for Intelligent Computing"},{"name":"Natural Science Foundation of China","award":["62002194"],"award-info":[{"award-number":["62002194"]}]},{"name":"Tsinghua University Guoqiang Research Institute"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591651","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:23Z","timestamp":1689726143000},"page":"131-140","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Constructing Tree-based Index for Efficient and Effective Dense Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8766-8610","authenticated-orcid":false,"given":"Haitao","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua University & Zhongguancun Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5030-709X","authenticated-orcid":false,"given":"Qingyao","family":"Ai","sequence":"additional","affiliation":[{"name":"Tsinghua University & Zhongguancun Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7253-5245","authenticated-orcid":false,"given":"Jingtao","family":"Zhan","sequence":"additional","affiliation":[{"name":"Tsinghua University & Zhongguancun Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9257-5498","authenticated-orcid":false,"given":"Jiaxin","family":"Mao","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0140-4512","authenticated-orcid":false,"given":"Yiqun","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University & Zhongguancun Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7765-8466","authenticated-orcid":false,"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei Poisson Lab, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4214-7858","authenticated-orcid":false,"given":"Zhao","family":"Cao","sequence":"additional","affiliation":[{"name":"Huawei Poisson Lab, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"The inverted multi-index","author":"Babenko Artem","year":"2014","unstructured":"Artem Babenko and Victor Lempitsky. 2014. The inverted multi-index. IEEE transactions on pattern analysis and machine intelligence, Vol. 37, 6 (2014), 1247--1260."},{"key":"e_1_3_2_1_2_1","volume-title":"Annoy: approximate nearest neighbors in C\/Python optimized for memory usage and loading\/saving to disk. GitHub https:\/\/github. com\/spotify\/annoy","author":"Bernhardsson Erik","year":"2017","unstructured":"Erik Bernhardsson. 2017. Annoy: approximate nearest neighbors in C\/Python optimized for memory usage and loading\/saving to disk. GitHub https:\/\/github. com\/spotify\/annoy (2017)."},{"key":"e_1_3_2_1_3_1","unstructured":"Jia Chen Haitao Li Weihang Su Qingyao Ai and Yiqun Liu. [n. d.]. THUIR at WSDM Cup 2023 Task 1: Unbiased Learning to Rank. ([n. d.])."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2008.4761079"},{"key":"e_1_3_2_1_5_1","volume-title":"Overview of the TREC 2019 deep learning track. arXiv preprint arXiv:2003","author":"Craswell Nick","year":"2020","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, and Ellen M Voorhees. 2020a. Overview of the TREC 2019 deep learning track. arXiv preprint arXiv:2003.07820 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Overview of the TREC 2020 Deep Learning Track. ArXiv","volume":"2003","author":"Craswell Nick","year":"2020","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Fernando Campos, and Ellen M. Voorhees. 2020b. Overview of the TREC 2020 Deep Learning Track. ArXiv, Vol. abs\/2003.07820 (2020)."},{"key":"e_1_3_2_1_7_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_8_1","volume-title":"Incorporating Explicit Knowledge in Pre-trained Language Models for Passage Re-ranking. arXiv preprint arXiv:2204.11673","author":"Dong Qian","year":"2022","unstructured":"Qian Dong, Yiding Liu, Suqi Cheng, Shuaiqiang Wang, Zhicong Cheng, Shuzi Niu, and Dawei Yin. 2022. Incorporating Explicit Knowledge in Pre-trained Language Models for Passage Re-ranking. arXiv preprint arXiv:2204.11673 (2022)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-17120-8_49"},{"key":"e_1_3_2_1_10_1","first-page":"38912","article-title":"Recommender Forest for Efficient Retrieval","volume":"35","author":"Feng Chao","year":"2022","unstructured":"Chao Feng, Wuchao Li, Defu Lian, Zheng Liu, and Enhong Chen. 2022a. Recommender Forest for Efficient Retrieval. Advances in Neural Information Processing Systems, Vol. 35 (2022), 38912--38924.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531980"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72113-8_10"},{"key":"e_1_3_2_1_13_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_14_1","volume-title":"Product quantization for nearest neighbor search","author":"Jegou Herve","year":"2010","unstructured":"Herve Jegou, Matthijs Douze, and Cordelia Schmid. 2010. Product quantization for nearest neighbor search. IEEE transactions on pattern analysis and machine intelligence, Vol. 33, 1 (2010), 117--128."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_16_1","volume-title":"Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas O\u011fuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_18_1","volume-title":"Contextualized sparse representations for real-time open-domain question answering. arXiv preprint arXiv:1911.02896","author":"Lee Jinhyuk","year":"2019","unstructured":"Jinhyuk Lee, Minjoon Seo, Hannaneh Hajishirzi, and Jaewoo Kang. 2019. Contextualized sparse representations for real-time open-domain question answering. arXiv preprint arXiv:1911.02896 (2019)."},{"key":"e_1_3_2_1_19_1","volume-title":"Fine-tuning and Learning to Rank. arXiv preprint arXiv:2303.04710","author":"Li Haitao","year":"2023","unstructured":"Haitao Li, Jia Chen, Weihang Su, Qingyao Ai, and Yiqun Liu. 2023. Towards Better Web Search Performance: Pre-training, Fine-tuning and Learning to Rank. arXiv preprint arXiv:2303.04710 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Distilling dense representations for ranking using tightly-coupled teachers. arXiv preprint arXiv:2010.11386","author":"Lin Sheng-Chieh","year":"2020","unstructured":"Sheng-Chieh Lin, Jheng-Hong Yang, and Jimmy Lin. 2020. Distilling dense representations for ranking using tightly-coupled teachers. arXiv preprint arXiv:2010.11386 (2020)."},{"key":"e_1_3_2_1_21_1","first-page":"15359","article-title":"Label disentanglement in partition-based extreme multilabel classification","volume":"34","author":"Liu Xuanqing","year":"2021","unstructured":"Xuanqing Liu, Wei-Cheng Chang, Hsiang-Fu Yu, Cho-Jui Hsieh, and Inderjit Dhillon. 2021. Label disentanglement in partition-based extreme multilabel classification. Advances in Neural Information Processing Systems, Vol. 34 (2021), 15359--15369.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_22_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Fixing weight decay regularization in adam. (2018)."},{"key":"e_1_3_2_1_23_1","volume-title":"Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs","author":"Malkov Yu A","year":"2018","unstructured":"Yu A Malkov and Dmitry A Yashunin. 2018. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE transactions on pattern analysis and machine intelligence, Vol. 42, 4 (2018), 824--836."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463030"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00346"},{"key":"e_1_3_2_1_26_1","volume-title":"Flann-fast library for approximate nearest neighbors user manual. Computer Science Department","author":"Muja Marius","year":"2009","unstructured":"Marius Muja and David Lowe. 2009. Flann-fast library for approximate nearest neighbors user manual. Computer Science Department, University of British Columbia, Vancouver, BC, Canada, Vol. 5 (2009)."},{"key":"e_1_3_2_1_27_1","volume-title":"MS MARCO: A human generated machine reading comprehension dataset. In CoCo@ NIPs.","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A human generated machine reading comprehension dataset. In CoCo@ NIPs."},{"key":"e_1_3_2_1_28_1","volume-title":"Falconn: A Locality-sensitive Filtering Approach for Approximate Nearest Neighbor Search. arXiv preprint arXiv:2206.01382","author":"Pham Ninh","year":"2022","unstructured":"Ninh Pham and Tao Liu. 2022. Falconn: A Locality-sensitive Filtering Approach for Approximate Nearest Neighbor Search. arXiv preprint arXiv:2206.01382 (2022)."},{"key":"e_1_3_2_1_29_1","volume-title":"Daxiang Dong, Hua Wu, and Haifeng Wang.","author":"Qu Yingqi","year":"2020","unstructured":"Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, Daxiang Dong, Hua Wu, and Haifeng Wang. 2020. RocketQA: An optimized training approach to dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2010.08191 (2020)."},{"key":"e_1_3_2_1_30_1","unstructured":"Yi Tay Vinh Q Tran Mostafa Dehghani Jianmo Ni Dara Bahri Harsh Mehta Zhen Qin Kai Hui Zhe Zhao Jai Gupta et al. 2022. Transformer memory as a differentiable search index. arXiv preprint arXiv:2202.06991 (2022)."},{"key":"e_1_3_2_1_31_1","unstructured":"Yujing Wang Yingyan Hou Haonan Wang Ziming Miao Shibin Wu Hao Sun Qi Chen Yuqing Xia Chengmin Chi Guoshuai Zhao et al. 2022. A Neural Corpus Indexer for Document Retrieval. arXiv preprint arXiv:2206.02743 (2022)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974010.105"},{"key":"e_1_3_2_1_33_1","unstructured":"Xiaohui Xie Qian Dong Bingning Wang Feiyang Lv Ting Yao Weinan Gan Zhijing Wu Xiangsheng Li Haitao Li Yiqun Liu et al. 2023. T2Ranking: A large-scale Chinese Benchmark for Passage Ranking. arXiv preprint arXiv:2304.03679 (2023)."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of NTCIR-16","author":"Yang Shenghao","year":"2022","unstructured":"Shenghao Yang, Haitao Li, Zhumin Chu, Jingtao Zhan, Yiqun Liu, Min Zhang, and Shaoping Ma. 2022. THUIR at the NTCIR-16 WWW-4 Task. Proceedings of NTCIR-16. to appear (2022)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-24755-2_3"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482358"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462880"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498443"},{"key":"e_1_3_2_1_39_1","volume-title":"RepBERT: Contextualized text embeddings for first-stage retrieval. arXiv preprint arXiv:2006.15498","author":"Zhan Jingtao","year":"2020","unstructured":"Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Min Zhang, and Shaoping Ma. 2020. RepBERT: Contextualized text embeddings for first-stage retrieval. arXiv preprint arXiv:2006.15498 (2020)."},{"key":"e_1_3_2_1_40_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Zhu Han","year":"2019","unstructured":"Han Zhu, Daqing Chang, Ziru Xu, Pengye Zhang, Xiang Li, Jie He, Han Li, Jian Xu, and Kun Gai. 2019. Joint optimization of tree-based index and deep model for recommender systems. Advances in Neural Information Processing Systems , Vol. 32 (2019)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219826"},{"key":"e_1_3_2_1_42_1","volume-title":"International Conference on Machine Learning. PMLR, 11650--11659","author":"Zhuo Jingwei","year":"2020","unstructured":"Jingwei Zhuo, Ziru Xu, Wei Dai, Han Zhu, Han Li, Jian Xu, and Kun Gai. 2020. Learning optimal tree models under beam search. In International Conference on Machine Learning. PMLR, 11650--11659."}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591651","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:40Z","timestamp":1750182700000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591651"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":42,"alternative-id":["10.1145\/3539618.3591651","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591651","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}