{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T04:28:29Z","timestamp":1769747309594,"version":"3.49.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031434143","type":"print"},{"value":"9783031434150","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-43415-0_37","type":"book-chapter","created":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T08:01:51Z","timestamp":1694851311000},"page":"630-647","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders Are Better Dense Retrievers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0650-9521","authenticated-orcid":false,"given":"Kun","family":"Zhou","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8893-366X","authenticated-orcid":false,"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9954-9674","authenticated-orcid":false,"given":"Yeyun","family":"Gong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8333-6196","authenticated-orcid":false,"given":"Wayne Xin","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6657-5806","authenticated-orcid":false,"given":"Daxin","family":"Jiang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3387-4674","authenticated-orcid":false,"given":"Nan","family":"Duan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9777-9676","authenticated-orcid":false,"given":"Ji-Rong","family":"Wen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,17]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Craswell, N., Mitra, B., Yilmaz, E., Campos, D.: Overview of the TREC 2020 deep learning track. arXiv preprint arXiv:2102.07662 (2021)","DOI":"10.6028\/NIST.SP.1266.deep-overview"},{"key":"37_CR2","doi-asserted-by":"crossref","unstructured":"Craswell, N., Mitra, B., Yilmaz, E., Campos, D., Voorhees, E.M.: Overview of the TREC 2019 deep learning track. arXiv preprint arXiv:2003.07820 (2020)","DOI":"10.6028\/NIST.SP.1266.deep-overview"},{"key":"37_CR3","doi-asserted-by":"publisher","unstructured":"Dai, Z., Callan, J.: Deeper text understanding for IR with contextual neural language modeling. In: Proceedings of SIGIR 2019, pp. 985\u2013988 (2019). https:\/\/doi.org\/10.1145\/3331184.3331303","DOI":"10.1145\/3331184.3331303"},{"key":"37_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL 2019, pp. 4171\u20134186 (2019). https:\/\/aclanthology.org\/N19-1423"},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Gao, L., Callan, J.: Condenser: a pre-training architecture for dense retrieval. In: Proceedings of EMNLP 2021, pp. 981\u2013993 (2021). https:\/\/aclanthology.org\/2021.emnlp-main.75","DOI":"10.18653\/v1\/2021.emnlp-main.75"},{"key":"37_CR6","unstructured":"Gao, L., Callan, J.: Is your language model ready for dense representation fine-tuning? arXiv preprint arXiv:2104.08253 (2021)"},{"key":"37_CR7","doi-asserted-by":"publisher","unstructured":"Gao, L., Callan, J.: Unsupervised corpus aware language model pre-training for dense passage retrieval. In: Proceedings of ACL 2022, pp. 2843\u20132853 (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.203","DOI":"10.18653\/v1\/2022.acl-long.203"},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Gao, L., Dai, Z., Callan, J.: COIL: revisit exact lexical match in information retrieval with contextualized inverted list. In: Proceedings of NAACL 2021, pp. 3030\u20133042 (2021).https:\/\/aclanthology.org\/2021.naacl-main.241","DOI":"10.18653\/v1\/2021.naacl-main.241"},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"37_CR10","doi-asserted-by":"publisher","unstructured":"Hofst\u00e4tter, S., Lin, S., Yang, J., Lin, J., Hanbury, A.: Efficiently teaching an effective dense retriever with balanced topic aware sampling. In: Proceedings of SIGIR 2021, pp. 113\u2013122 (2021). https:\/\/doi.org\/10.1145\/3404835.3462891","DOI":"10.1145\/3404835.3462891"},{"key":"37_CR11","doi-asserted-by":"publisher","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with gpus. IEEE Trans. Big Data 7(3), 535\u2013547 (2021). https:\/\/doi.org\/10.1109\/TBDATA.2019.2921572","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: Proceedings of EMNLP 2020, pp. 6769\u20136781 (2020). https:\/\/aclanthology.org\/2020.emnlp-main.550","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"37_CR13","doi-asserted-by":"publisher","unstructured":"Khattab, O., Zaharia, M.: Colbert: efficient and effective passage search via contextualized late interaction over BERT. In: Proceedings of SIGIR 2020, pp. 39\u201348 (2020). https:\/\/doi.org\/10.1145\/3397271.3401075","DOI":"10.1145\/3397271.3401075"},{"key":"37_CR14","doi-asserted-by":"crossref","unstructured":"Kwiatkowski, T., et al.: Natural questions: a benchmark for question answering research. Trans. Assoc. Comput. Linguist. 7, 452\u2013466 (2019). https:\/\/aclanthology.org\/Q19-1026","DOI":"10.1162\/tacl_a_00276"},{"key":"37_CR15","doi-asserted-by":"crossref","unstructured":"Lee, K., Chang, M.W., Toutanova, K.: Latent retrieval for weakly supervised open domain question answering. In: Proceedings of ACL 2019, pp. 6086\u20136096 (2019). https:\/\/aclanthology.org\/P19-1612","DOI":"10.18653\/v1\/P19-1612"},{"key":"37_CR16","doi-asserted-by":"crossref","unstructured":"Lin, Z., et al.: Prod: progressive distillation for dense retrieval. In: Proceedings of the ACM Web Conference 2023, pp. 3299\u20133308 (2023)","DOI":"10.1145\/3543507.3583421"},{"key":"37_CR17","unstructured":"Liu, Z., Shao, Y.: Retromae: pre-training retrieval-oriented transformers via masked auto-encoder. arXiv preprint arXiv:2205.12035 (2022)"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Lu, S., et al.: Less is more: pretrain a strong Siamese encoder for dense text retrieval using a weak decoder. In: Proceedings of EMNLP 2021, pp. 2780\u20132791 (2021). https:\/\/aclanthology.org\/2021.emnlp-main.220","DOI":"10.18653\/v1\/2021.emnlp-main.220"},{"key":"37_CR19","doi-asserted-by":"publisher","unstructured":"Lu, Y., et al.: Ernie-search: bridging cross-encoder with dual-encoder via self on-the-fly distillation for dense passage retrieval. arXiv preprint arXiv:2205.09153 (2022). https:\/\/doi.org\/10.48550\/arXiv.2205.09153","DOI":"10.48550\/arXiv.2205.09153"},{"key":"37_CR20","unstructured":"Ma, G., Wu, X., Wang, P., Hu, S.: Cot-mote: exploring contextual masked auto-encoder pre-training with mixture-of-textual-experts for passage retrieval. arXiv preprint arXiv:2304.10195 (2023)"},{"key":"37_CR21","doi-asserted-by":"publisher","unstructured":"Ma, X., Guo, J., Zhang, R., Fan, Y., Cheng, X.: Pre-train a discriminative text encoder for dense retrieval via contrastive span prediction. In: Proceedings of SIGIR 2022, pp. 848\u2013858 (2022). https:\/\/doi.org\/10.1145\/3477495.3531772","DOI":"10.1145\/3477495.3531772"},{"key":"37_CR22","unstructured":"Nguyen, T., et al.: MS MARCO: a human generated machine reading comprehension dataset. In: Proceedings of the Workshop on Cognitive Computation: Integrating Neural and Symbolic Approaches 2016, vol.\u00a01773 (2016). http:\/\/ceur-ws.org\/Vol-1773\/CoCoNIPS_2016_paper9.pdf"},{"key":"37_CR23","unstructured":"Nogueira, R., Lin, J.: From doc2query to doctttttquery (2019). https:\/\/cs.uwaterloo.ca\/~jimmylin\/publications\/Nogueira_Lin_2019_docTTTTTquery.pdf"},{"key":"37_CR24","unstructured":"Nogueira, R.F., Yang, W., Lin, J., Cho, K.: Document expansion by query prediction. arXiv preprint arXiv:1904.08375 (2019)"},{"key":"37_CR25","doi-asserted-by":"crossref","unstructured":"Qu, Y., et al.: RocketQA: an optimized training approach to dense passage retrieval for open-domain question answering. In: Proceedings of NAACL 2021, pp. 5835\u20135847 (2021). https:\/\/aclanthology.org\/2021.naacl-main.466","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"37_CR26","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners (2019). https:\/\/cdn.openai.com\/better-language-models\/language_models_are_unsupervised_multitask_learners.pdf"},{"key":"37_CR27","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140:1\u2013140:67 (2020). http:\/\/jmlr.org\/papers\/v21\/20-074.html"},{"key":"37_CR28","unstructured":"Ramos, J., et al.: Using TF-IDF to determine word relevance in document queries. In: Proceedings of the First Instructional Conference on Machine Learning, vol. 242, pp. 29\u201348 (2003)"},{"key":"37_CR29","doi-asserted-by":"crossref","unstructured":"Ren, R., et al.: PAIR: Leveraging passage-centric similarity relation for improving dense passage retrieval. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 2173\u20132183 (2021). https:\/\/aclanthology.org\/2021.findings-acl.191","DOI":"10.18653\/v1\/2021.findings-acl.191"},{"key":"37_CR30","doi-asserted-by":"crossref","unstructured":"Ren, R., et al.: Rocketqav2: a joint training method for dense passage retrieval and passage re-ranking. In: Proceedings of EMNLP 2021, pp. 2825\u20132835 (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.224","DOI":"10.18653\/v1\/2021.emnlp-main.224"},{"key":"37_CR31","doi-asserted-by":"crossref","unstructured":"Santhanam, K., Khattab, O., Saad-Falcon, J., Potts, C., Zaharia, M.: Colbertv2: effective and efficient retrieval via lightweight late interaction. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, WA, United States, 10\u201315 July 2022, pp. 3715\u20133734 (2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.272","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"37_CR32","unstructured":"Sun, H., et al.: Lead: liberal feature-based distillation for dense retrieval. arXiv preprint arXiv:2212.05225 (2022)"},{"key":"37_CR33","unstructured":"Thakur, N., Reimers, N., R\u00fcckl\u00e9, A., Srivastava, A., Gurevych, I.: BEIR: a heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663 (2021)"},{"key":"37_CR34","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. In: Proceedings of ICLR 2019 (2019). https:\/\/openreview.net\/forum?id=rJ4km2R5t7"},{"key":"37_CR35","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Simlm: pre-training with representation bottleneck for dense passage retrieval. arXiv preprint arXiv:2207.02578 (2022)","DOI":"10.18653\/v1\/2023.acl-long.125"},{"key":"37_CR36","doi-asserted-by":"crossref","unstructured":"Wu, X., Ma, G., Lin, M., Lin, Z., Wang, Z., Hu, S.: Contextual mask auto-encoder for dense passage retrieval. arXiv preprint arXiv:2208.07670 (2022)","DOI":"10.1609\/aaai.v37i4.25598"},{"key":"37_CR37","unstructured":"Wu, X., et al.: Cot-mae v2: contextual masked auto-encoder with multi-view modeling for passage retrieval. arXiv preprint arXiv:2304.03158 (2023)"},{"key":"37_CR38","unstructured":"Xiao, S., Liu, Z.: Retromae v2: duplex masked auto-encoder for pre-training retrieval-oriented language models. arXiv preprint arXiv:2211.08769 (2022)"},{"key":"37_CR39","unstructured":"Xiong, L., et al.: Approximate nearest neighbor negative contrastive learning for dense text retrieval. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3\u20137 May 2021 (2021). https:\/\/openreview.net\/forum?id=zeFrfgyZln"},{"key":"37_CR40","doi-asserted-by":"crossref","unstructured":"Yang, P., Fang, H., Lin, J.: Anserini: enabling the use of lucene for information retrieval research. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Shinjuku, Tokyo, Japan, 7\u201311 August 2017, pp. 1253\u20131256 (2017). https:\/\/doi.org\/10.1145\/3077136.3080721","DOI":"10.1145\/3077136.3080721"},{"key":"37_CR41","doi-asserted-by":"crossref","unstructured":"Zhan, J., Mao, J., Liu, Y., Guo, J., Zhang, M., Ma, S.: Optimizing dense retrieval model training with hard negatives. In: SIGIR \u201921: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, 11\u201315 July 2021, pp. 1503\u20131512 (2021). https:\/\/doi.org\/10.1145\/3404835.3462880","DOI":"10.1145\/3404835.3462880"},{"key":"37_CR42","unstructured":"Zhang, H., Gong, Y., Shen, Y., Lv, J., Duan, N., Chen, W.: Adversarial retriever-ranker for dense text retrieval. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25\u201329 April 2022 (2022). https:\/\/openreview.net\/forum?id=MR7XubKUFB"},{"key":"37_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, W.X., Liu, J., Ren, R., Wen, J.R.: Dense text retrieval based on pretrained language models: a survey. arXiv preprint arXiv:2211.14876 (2022)","DOI":"10.1145\/3637870"},{"key":"37_CR44","unstructured":"Zhao, W.X., et al.: A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)"},{"key":"37_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, K., et al.: Simans: simple ambiguous negatives sampling for dense text retrieval. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2022)","DOI":"10.18653\/v1\/2022.emnlp-industry.56"},{"key":"37_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, K., Zhang, B., Zhao, W.X., Wen, J.R.: Debiased contrastive learning of unsupervised sentence representations. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 6120\u20136130 (2022)","DOI":"10.18653\/v1\/2022.acl-long.423"},{"key":"37_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, Y.J., Yao, J., Dou, Z.C., Wu, L., Wen, J.R.: Dynamicretriever: a pre-trained model-based IR system without an explicit index. In: Machine Intelligence Research, pp. 1\u201313 (2023)","DOI":"10.1007\/s11633-022-1373-9"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases: Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43415-0_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T05:50:39Z","timestamp":1730094639000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43415-0_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031434143","9783031434150"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43415-0_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"17 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"829","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"196","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.63","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Applied Data Science Track: 239 submissions, 58 accepted papers; Demo Track: 31 submissions, 16 accepted papers.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}