{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T06:01:10Z","timestamp":1777615270501,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":40,"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\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657792","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"1818-1827","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval."],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6916-9611","authenticated-orcid":false,"given":"Guangyuan","family":"Ma","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3796-3705","authenticated-orcid":false,"given":"Xing","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1390-7424","authenticated-orcid":false,"given":"Zijia","family":"Lin","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7170-3809","authenticated-orcid":false,"given":"Songlin","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591956"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19--1423"},{"key":"e_1_3_2_1_3_1","volume-title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. CoRR","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, Carlos Lassance, Benjamin Piwowarski, and St\u00e9 phane Clinchant. 2021a. SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. CoRR , Vol. abs\/2109.10086 (2021). showeprint[arXiv]2109.10086 https:\/\/arxiv.org\/abs\/2109.10086"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531857"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463098"},{"key":"e_1_3_2_1_6_1","unstructured":"Wikimedia Foundation. [n. d.]. Wikimedia Downloads. https:\/\/dumps.wikimedia.org"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.75"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.203"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063576.2063981"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.03653"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/P17--1147"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/TACL_A_00276"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.13197"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.148"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.220"},{"key":"e_1_3_2_1_17_1","volume-title":"Hao Tian, Hua Wu, Shuaiqiang Wang, Dawei Yin, et al.","author":"Lu Yuxiang","year":"2022","unstructured":"Yuxiang Lu, Yiding Liu, Jiaxiang Liu, Yunsheng Shi, Zhengjie Huang, Shikun Feng Yu Sun, Hao Tian, Hua Wu, Shuaiqiang Wang, Dawei Yin, et al. 2022. Ernie-search: Bridging cross-encoder with dual-encoder via self on-the-fly distillation for dense passage retrieval. arXiv preprint arXiv:2205.09153 (2022)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19--24, 2016 (JMLR Workshop and Conference Proceedings","volume":"2596","author":"Mussmann Stephen","year":"2016","unstructured":"Stephen Mussmann and Stefano Ermon. 2016. Learning and Inference via Maximum Inner Product Search. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19--24, 2016 (JMLR Workshop and Conference Proceedings, Vol. 48), Maria-Florina Balcan and Kilian Q. Weinberger (Eds.). JMLR.org, 2587--2596. http:\/\/proceedings.mlr.press\/v48\/mussmann16.html"},{"key":"e_1_3_2_1_20_1","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 Proceedings of the Workshop on Cognitive Computation: Integrating neural and symbolic approaches 2016 co-located with the 30th Annual Conference on Neural Information Processing Systems (NIPS 2016) Barcelona Spain December 9 2016 (CEUR Workshop Proceedings Vol. 1773) Tarek Richard Besold Antoine Bordes Artur S. d'Avila Garcez and Greg Wayne (Eds.). CEUR-WS.org. https:\/\/ceur-ws.org\/Vol-1773\/CoCoNIPS_2016_paper9.pdf"},{"key":"e_1_3_2_1_21_1","volume-title":"Document Expansion by Query Prediction. CoRR","author":"Nogueira Rodrigo Frassetto","year":"2019","unstructured":"Rodrigo Frassetto Nogueira, Wei Yang, Jimmy Lin, and Kyunghyun Cho. 2019. Document Expansion by Query Prediction. CoRR , Vol. abs\/1904.08375 (2019). showeprint[arXiv]1904.08375 http:\/\/arxiv.org\/abs\/1904.08375"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"e_1_3_2_1_23_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.ACL-LONG.140"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.224"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_27_1","volume-title":"LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval. In The Eleventh International Conference on Learning Representations, ICLR 2023","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, ICLR 2023, Kigali, Rwanda, May 1--5, 2023. OpenReview.net. https:\/\/openreview.net\/pdf?id=PfpEtB3-csK"},{"key":"e_1_3_2_1_28_1","volume-title":"Abhishek Srivastava, and Iryna Gurevych.","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fc ckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models. CoRR , Vol. abs\/2104.08663 (2021). showeprint[arXiv]2104.08663 https:\/\/arxiv.org\/abs\/2104.08663"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","unstructured":"Liang Wang Nan Yang Xiaolong Huang Binxing Jiao Linjun Yang Daxin Jiang Rangan Majumder and Furu Wei. 2023 b. SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval. (2023) 2244--2258. https:\/\/doi.org\/10.18653\/V1\/2023.ACL-LONG.125","DOI":"10.18653\/V1\/2023.ACL-LONG.125"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Liang Wang Nan Yang and Furu Wei. 2023 a. Query2doc: Query Expansion with Large Language Models. (2023) 9414--9423. https:\/\/doi.org\/10.18653\/V1\/2023.EMNLP-MAIN.585","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.585"},{"key":"e_1_3_2_1_31_1","volume-title":"Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI","author":"Wu Xing","year":"2023","unstructured":"Xing Wu, Guangyuan Ma, Meng Lin, Zijia Lin, Zhongyuan Wang, and Songlin Hu. 2023 a. ConTextual Masked Auto-Encoder for Dense Passage Retrieval. In Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI 2023, Thirteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2023, Washington, DC, USA, February 7--14, 2023, Brian Williams, Yiling Chen, and Jennifer Neville (Eds.). AAAI Press, 4738--4746. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/25598"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.118"},{"key":"e_1_3_2_1_33_1","unstructured":"Xing Wu Guangyuan Ma Peng Wang Meng Lin Zijia Lin Fuzheng Zhang and Songlin Hu. 2023 c. CoT-MAE v2: Contextual Masked Auto-Encoder with Multi-view Modeling for Passage Retrieval. arxiv: 2304.03158 [cs.CL]"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2022.EMNLP-MAIN.35"},{"key":"e_1_3_2_1_35_1","unstructured":"Lee Xiong Chenyan Xiong Ye Li Kwok-Fung Tang Jialin Liu Paul N. Bennett Junaid Ahmed and Arnold Overwijk. 2021. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. (2021). https:\/\/openreview.net\/forum?id=zeFrfgyZln"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.31193\/ssap.01.9787509752807"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-031--56063--7_12"},{"key":"e_1_3_2_1_38_1","volume-title":"Daxin Jiang, Nan Duan, and Ji-Rong Wen.","author":"Zhou Kun","year":"2022","unstructured":"Kun Zhou, Xiao Liu, Yeyun Gong, Wayne Xin Zhao, Daxin Jiang, Nan Duan, and Ji-Rong Wen. 2022. MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers. arXiv preprint arXiv:2212.07841 (2022)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462922"}],"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\/3626772.3657792","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657792","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:42:40Z","timestamp":1755841360000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657792"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":40,"alternative-id":["10.1145\/3626772.3657792","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657792","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"}}]}}