{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T04:24:43Z","timestamp":1778300683398,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589335.3648327","type":"proceedings-article","created":{"date-parts":[[2024,5,12]],"date-time":"2024-05-12T18:41:21Z","timestamp":1715539281000},"page":"292-301","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["MS MARCO Web Search: A Large-scale Information-rich Web Dataset with Millions of Real Click Labels"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7394-0185","authenticated-orcid":false,"given":"Qi","family":"Chen","sequence":"first","affiliation":[{"name":"Microsoft, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6477-7933","authenticated-orcid":false,"given":"Xiubo","family":"Geng","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9167-6214","authenticated-orcid":false,"given":"Corby","family":"Rosset","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2182-5145","authenticated-orcid":false,"given":"Carolyn","family":"Buractaon","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8208-898X","authenticated-orcid":false,"given":"Jingwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3315-2468","authenticated-orcid":false,"given":"Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0650-9521","authenticated-orcid":false,"given":"Kun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0392-4183","authenticated-orcid":false,"given":"Chenyan","family":"Xiong","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9954-9674","authenticated-orcid":false,"given":"Yeyun","family":"Gong","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7852-9651","authenticated-orcid":false,"given":"Paul","family":"Bennett","sequence":"additional","affiliation":[{"name":"Spotify, New York, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9351-8137","authenticated-orcid":false,"given":"Nick","family":"Craswell","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8608-8482","authenticated-orcid":false,"given":"Xing","family":"Xie","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0378-060X","authenticated-orcid":false,"given":"Fan","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3659-6988","authenticated-orcid":false,"given":"Bryan","family":"Tower","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0281-932X","authenticated-orcid":false,"given":"Nikhil","family":"Rao","sequence":"additional","affiliation":[{"name":"Microsoft, Mountain View, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8241-4746","authenticated-orcid":false,"given":"Anlei","family":"Dong","sequence":"additional","affiliation":[{"name":"Microsoft, Mountain View, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3895-7943","authenticated-orcid":false,"given":"Wenqi","family":"Jiang","sequence":"additional","affiliation":[{"name":"ETH Zurich, Z\u00fcrich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7765-8466","authenticated-orcid":false,"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0270-9489","authenticated-orcid":false,"given":"Mingqin","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0980-6936","authenticated-orcid":false,"given":"Chuanjie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8243-7769","authenticated-orcid":false,"given":"Zengzhong","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2430-575X","authenticated-orcid":false,"given":"Rangan","family":"Majumder","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1157-018X","authenticated-orcid":false,"given":"Jennifer","family":"Neville","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7208-2933","authenticated-orcid":false,"given":"Andy","family":"Oakley","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6503-8324","authenticated-orcid":false,"given":"Knut Magne","family":"Risvik","sequence":"additional","affiliation":[{"name":"Microsoft, Oslo, Norway"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9323-2227","authenticated-orcid":false,"given":"Harsha Vardhan","family":"Simhadri","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4516-6613","authenticated-orcid":false,"given":"Manik","family":"Varma","sequence":"additional","affiliation":[{"name":"Microsoft, Bengaluru, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7940-5216","authenticated-orcid":false,"given":"Yujing","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1778-7167","authenticated-orcid":false,"given":"Linjun","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6455-3898","authenticated-orcid":false,"given":"Mao","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8105-7505","authenticated-orcid":false,"given":"Ce","family":"Zhang","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDIS.1996.568672"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68474-1_3"},{"key":"e_1_3_2_2_3_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_2_4_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2055--2063","author":"Babenko Artem","year":"2016","unstructured":"Artem Babenko and Victor Lempitsky. 2016. Efficient indexing of billion-scale datasets of deep descriptors. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2055--2063."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_13"},{"key":"e_1_3_2_2_6_1","first-page":"31668","article-title":"Autoregressive search engines: Generating substrings as document identifiers","volume":"35","author":"Bevilacqua Michele","year":"2022","unstructured":"Michele Bevilacqua, Giuseppe Ottaviano, Patrick Lewis, Scott Yih, Sebastian Riedel, and Fabio Petroni. 2022. Autoregressive search engines: Generating substrings as document identifiers. Advances in Neural Information Processing Systems , Vol. 35 (2022), 31668--31683.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_7_1","unstructured":"Jamie Callan. 2012. The lemur project and its clueweb12 dataset. In Invited talk at the SIGIR 2012 Workshop on Open-Source Information Retrieval."},{"key":"e_1_3_2_2_8_1","first-page":"5199","article-title":"SPANN: Highly-efficient Billion-scale Approximate Nearest Neighborhood Search","volume":"34","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. Advances in Neural Information Processing Systems , Vol. 34 (2021), 5199--5212.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_9_1","volume-title":"Overview of the TREC 2004 Terabyte Track. In TREC.","author":"Clarke Charles","year":"2004","unstructured":"Charles Clarke, Nick Craswell, and Ian Soboroff. 2004. Overview of the TREC 2004 Terabyte Track. In TREC."},{"key":"e_1_3_2_2_10_1","volume-title":"Overview of the TREC 2009 Web Track.. In Trec","volume":"9","author":"Clarke Charles LA","year":"2009","unstructured":"Charles LA Clarke, Nick Craswell, and Ian Soboroff. 2009. Overview of the TREC 2009 Web Track.. In Trec, Vol. 9. 20--29."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412779"},{"key":"e_1_3_2_2_12_1","volume-title":"Context-aware sentence\/passage term importance estimation for first stage retrieval. arXiv preprint arXiv:1910.10687","author":"Dai Zhuyun","year":"2019","unstructured":"Zhuyun Dai and Jamie Callan. 2019. Context-aware sentence\/passage term importance estimation for first stage retrieval. arXiv preprint arXiv:1910.10687 (2019)."},{"key":"e_1_3_2_2_13_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_2_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.203"},{"key":"e_1_3_2_2_15_1","volume-title":"A caching relay for the world wide web. Computer Networks and ISDN systems","author":"Glassman Steven","year":"1994","unstructured":"Steven Glassman. 1994. A caching relay for the world wide web. Computer Networks and ISDN systems , Vol. 27, 2 (1994), 165--173."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3486250"},{"key":"e_1_3_2_2_17_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML). 3887--3896","author":"Guo Ruiqi","year":"2020","unstructured":"Ruiqi Guo, Philip Sun, Erik Lindgren, Quan Geng, David Simcha, Felix Chern, and Sanjiv Kumar. 2020. Accelerating Large-Scale Inference with Anisotropic Vector Quantization. In Proceedings of the 37th International Conference on Machine Learning (ICML). 3887--3896."},{"key":"e_1_3_2_2_18_1","unstructured":"Yelong Shen Jiancheng Lv Nan Duan Weizhu Chen Hang Zhang Yeyun Gong. 2022. Adversarial Retriever-Ranker model for Dense Retrieval. In ICLR."},{"key":"e_1_3_2_2_19_1","volume-title":"Convolutional neural network architectures for matching natural language sentences. Advances in neural information processing systems","author":"Hu Baotian","year":"2014","unstructured":"Baotian Hu, Zhengdong Lu, Hang Li, and Qingcai Chen. 2014. Convolutional neural network architectures for matching natural language sentences. Advances in neural information processing systems , Vol. 27 (2014)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_2_21_1","volume-title":"Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring. In International Conference on Learning Representations.","author":"Humeau Samuel","year":"2019","unstructured":"Samuel Humeau, Kurt Shuster, Marie-Anne Lachaux, and Jason Weston. 2019. Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_22_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_2_23_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_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946540"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.298"},{"key":"e_1_3_2_2_27_1","volume-title":"Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oug uz, 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_2_28_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_2_29_1","volume-title":"Naver Labs Europe (SPLADE)@ TREC Deep Learning","author":"Lassance Carlos","year":"2022","unstructured":"Carlos Lassance and St\u00e9phane Clinchant. 2023. Naver Labs Europe (SPLADE)@ TREC Deep Learning 2022. arXiv preprint arXiv:2302.12574 (2023)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.86"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412747"},{"key":"e_1_3_2_2_32_1","unstructured":"microsoft. [n. d.] a. Bing search. https:\/\/www.bing.com\/."},{"key":"e_1_3_2_2_33_1","unstructured":"microsoft. [n. d.] b. New Bing. https:\/\/www.bing.com\/new."},{"key":"e_1_3_2_2_34_1","volume-title":"Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332","author":"Nakano Reiichiro","year":"2021","unstructured":"Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, et al. 2021. Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332 (2021)."},{"key":"e_1_3_2_2_35_1","volume-title":"Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong Wook Kim, Chris Hallacy, et al.","author":"Neelakantan Arvind","year":"2022","unstructured":"Arvind Neelakantan, Tao Xu, Raul Puri, Alec Radford, Jesse Michael Han, Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong Wook Kim, Chris Hallacy, et al. 2022. Text and code embeddings by contrastive pre-training. arXiv preprint arXiv:2201.10005 (2022)."},{"key":"e_1_3_2_2_36_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_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3536321"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2520371"},{"key":"e_1_3_2_2_39_1","volume-title":"Understanding the Behaviors of BERT in Ranking. arXiv preprint arXiv:1904.07531","author":"Qiao Yifan","year":"2019","unstructured":"Yifan Qiao, Chenyan Xiong, Zhenghao Liu, and Zhiyuan Liu. 2019. Understanding the Behaviors of BERT in Ranking. arXiv preprint arXiv:1904.07531 (2019)."},{"key":"e_1_3_2_2_40_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_2_41_1","volume-title":"HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory. In In Proceedings of the 34th International Conference on Neural Information Processing Systems","volume":"33","author":"Ren Jie","year":"2020","unstructured":"Jie Ren, Minjia Zhang, and Dong Li. 2020. HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory. In In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vol. 33."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2099-5_24"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2073"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1436"},{"key":"e_1_3_2_2_45_1","volume-title":"GLOW: Global Weighted Self-Attention Network for Web Search. In 2021 IEEE International Conference on Big Data (Big Data). IEEE, 519--528","author":"Shan Xuan","year":"2021","unstructured":"Xuan Shan, Chuanjie Liu, Yiqian Xia, Qi Chen, Yusi Zhang, Kaize Ding, Yaobo Liang, Angen Luo, and Yuxiang Luo. 2021. GLOW: Global Weighted Self-Attention Network for Web Search. In 2021 IEEE International Conference on Big Data (Big Data). IEEE, 519--528."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2567948.2577348"},{"key":"e_1_3_2_2_47_1","volume-title":"Overview of TREC 2021. In 30th Text REtrieval Conference","author":"Soboroff Ian","year":"2021","unstructured":"Ian Soboroff. 2021. Overview of TREC 2021. In 30th Text REtrieval Conference. Gaithersburg, Maryland."},{"key":"e_1_3_2_2_48_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems. 13766--13776","author":"Subramanya Suhas Jayaram","year":"2019","unstructured":"Suhas Jayaram Subramanya, Rohan Kadekodi, Ravishankar Krishaswamy, and Harsha Vardhan Simhadri. 2019. Diskann: Fast accurate billion-point nearest neighbor search on a single node. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. 13766--13776."},{"key":"e_1_3_2_2_49_1","first-page":"21831","article-title":"Transformer memory as a differentiable search index","volume":"35","author":"Tay Yi","year":"2022","unstructured":"Yi Tay, Vinh 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. Advances in Neural Information Processing Systems , Vol. 35 (2022), 21831--21843.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_50_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_2_51_1","first-page":"25600","article-title":"A neural corpus indexer for document retrieval","volume":"35","author":"Wang Yujing","year":"2022","unstructured":"Yujing Wang, Yingyan Hou, Haonan Wang, Ziming Miao, Shibin Wu, Qi Chen, Yuqing Xia, Chengmin Chi, Guoshuai Zhao, Zheng Liu, et al. 2022. A neural corpus indexer for document retrieval. Advances in Neural Information Processing Systems , Vol. 35 (2022), 25600--25614.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531799"},{"key":"e_1_3_2_2_53_1","volume-title":"Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808","author":"Xiong Lee","year":"2020","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808 (2020)."},{"key":"e_1_3_2_2_54_1","volume-title":"Leveraging Advantages of Interactive and Non-Interactive Models for Vector-Based Cross-Lingual Information Retrieval. arXiv preprint arXiv:2111.01992","author":"Xu Linlong","year":"2021","unstructured":"Linlong Xu, Baosong Yang, Xiaoyu Lv, Tianchi Bi, Dayiheng Liu, and Haibo Zhang. 2021. Leveraging Advantages of Interactive and Non-Interactive Models for Vector-Based Cross-Lingual Information Retrieval. arXiv preprint arXiv:2111.01992 (2021)."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557312"},{"key":"e_1_3_2_2_56_1","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track. 548--559","author":"Zhou Kun","year":"2022","unstructured":"Kun Zhou, Yeyun Gong, Xiao Liu, Wayne Xin Zhao, Yelong Shen, Anlei Dong, Jingwen Lu, Rangan Majumder, Ji-Rong Wen, and Nan Duan. 2022. SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track. 548--559."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"crossref","unstructured":"Shengyao Zhuang Hang Li and G. Zuccon. 2021. Deep Query Likelihood Model for Information Retrieval. In ECIR. io","DOI":"10.1007\/978-3-030-72240-1_49"}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3648327","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589335.3648327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:37:16Z","timestamp":1755823036000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3648327"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":57,"alternative-id":["10.1145\/3589335.3648327","10.1145\/3589335"],"URL":"https:\/\/doi.org\/10.1145\/3589335.3648327","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}