{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T09:07:49Z","timestamp":1784970469364,"version":"3.55.0"},"reference-count":155,"publisher":"Association for Computing Machinery (ACM)","issue":"7","license":[{"start":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T00:00:00Z","timestamp":1712620800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Science and Engineering Research Council (NSERC) of Canada","award":["RGPIN-2020-07157"],"award-info":[{"award-number":["RGPIN-2020-07157"]}]},{"name":"York Research Chairs"},{"name":"Ontario Research Fund-Research Excellence"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2024,7,31]]},"abstract":"<jats:p>Recent years have witnessed a substantial increase in the use of deep learning to solve various natural language processing (NLP) problems. Early deep learning models were constrained by their sequential or unidirectional nature, such that they struggled to capture the contextual relationships across text inputs. The introduction of bidirectional encoder representations from transformers (BERT) leads to a robust encoder for the transformer model that can understand the broader context and deliver state-of-the-art performance across various NLP tasks. This has inspired researchers and practitioners to apply BERT to practical problems, such as information retrieval (IR). A survey that focuses on a comprehensive analysis of prevalent approaches that apply pretrained transformer encoders like BERT to IR can thus be useful for academia and the industry. In light of this, we revisit a variety of BERT-based methods in this survey, cover a wide range of techniques of IR, and group them into six high-level categories: (i) handling long documents, (ii) integrating semantic information, (iii) balancing effectiveness and efficiency, (iv) predicting the weights of terms, (v) query expansion, and (vi) document expansion. We also provide links to resources, including datasets and toolkits, for BERT-based IR systems. Additionally, we highlight the advantages of employing encoder-based BERT models in contrast to recent large language models like ChatGPT, which are decoder-based and demand extensive computational resources. Finally, we summarize the comprehensive outcomes of the survey and suggest directions for future research in the area.<\/jats:p>","DOI":"10.1145\/3648471","type":"journal-article","created":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T05:17:12Z","timestamp":1707974232000},"page":"1-33","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":107,"title":["Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges"],"prefix":"10.1145","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8086-4607","authenticated-orcid":false,"given":"Jiajia","family":"Wang","sequence":"first","affiliation":[{"name":"School of Sciences, Henan University of Technology, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1292-1491","authenticated-orcid":false,"given":"Jimmy Xiangji","family":"Huang","sequence":"additional","affiliation":[{"name":"Information Retrieval and Knowledge Management Research Lab, York University, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6570-009X","authenticated-orcid":false,"given":"Xinhui","family":"Tu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Central China Normal University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0804-4281","authenticated-orcid":false,"given":"Junmei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1644-4696","authenticated-orcid":false,"given":"Angela Jennifer","family":"Huang","sequence":"additional","affiliation":[{"name":"Lassonde School of Engineering, York University, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7880-299X","authenticated-orcid":false,"given":"Md Tahmid Rahman","family":"Laskar","sequence":"additional","affiliation":[{"name":"York University &amp; Dialpad Inc., Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2069-0753","authenticated-orcid":false,"given":"Amran","family":"Bhuiyan","sequence":"additional","affiliation":[{"name":"Information Retrieval and Knowledge Management Research Lab, York University, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,9]]},"reference":[{"key":"e_1_3_3_2_2","volume-title":"European Conference on Information Retrieval. Springer, Cham.","author":"Abolghasemi A.","unstructured":"A. Abolghasemi, S. Verberne, and L. Azzopardi. 2022. Improving BERT-based query-by-document retrieval with multi-task optimization. In European Conference on Information Retrieval. Springer, Cham."},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37899-7_16"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1736359"},{"key":"e_1_3_3_5_2","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery A.","year":"2023","unstructured":"A. Chowdhery, S. Narang, J. Devlin, M. Bosma et\u00a0al. 2023. Palm: Scaling language modeling with pathways. J. Mach. Learn. Res. 24, 240 (2023), 1\u2013113.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"e_1_3_3_7_2","volume-title":"Proceedings of the International Conference on Information Management and Engineering. IEEE, 385\u2013389","author":"Lashkari A. H.","unstructured":"A. H. Lashkari, F. Mahdavi, and V. Ghomi. 2009. A boolean model in information retrieval for search engines. In Proceedings of the International Conference on Information Management and Engineering. IEEE, 385\u2013389."},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09825-6"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_3_10_2","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1723\u20131727","author":"Mallia A.","unstructured":"A. Mallia, O. Khattab, T. Suel, and N. Tonellotto. 2021. Learning passage impacts for inverted indexes. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1723\u20131727."},{"key":"e_1_3_3_11_2","unstructured":"A. Radford K. Narasimhan T. Salimans and I. Sutskever. 2018. Improving language understanding by generative pre-training."},{"key":"e_1_3_3_12_2","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. 1073-1083","author":"Liu P. J.","unstructured":"A. See, P. J. Liu, and C. D. Manning. 2017. Get to the point: Summarization with pointer-generator networks. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. 1073-1083."},{"key":"e_1_3_3_13_2","volume-title":"Proceedings of Advances in Neural Information Processing Systems, 30","author":"Vaswani A.","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin. 2017. Attention is all you need. In Proceedings of Advances in Neural Information Processing Systems, 30."},{"key":"e_1_3_3_14_2","volume-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv:1804.07461.","author":"Wang A.","year":"2018","unstructured":"A. Wang, A. Singh, J. Michael, F. Hill, O. Levy, and S. R. Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv:1804.07461. Retrieved from https:\/\/arxiv.org\/abs\/1804.07461"},{"key":"e_1_3_3_15_2","volume-title":"Proceedings of the 13th International Conference on Web Search and Data Mining. 861\u2013864","author":"Yates A.","unstructured":"A. Yates, S. Arora, X. Zhang, W. Yang, K. M. Jose, and J. Lin. 2020. Capreolus: A toolkit for end-to-end neural ad hoc retrieval. In Proceedings of the 13th International Conference on Web Search and Data Mining. 861\u2013864."},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09794-5"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2011.03.007"},{"key":"e_1_3_3_18_2","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems","volume":"2","author":"Hu B.","year":"2042","unstructured":"B. Hu, Z. Lu, H. Li, and Q. Chen. 2014. Convolutional neural network architectures for matching natural language sentences. In Proceedings of the 27th International Conference on Neural Information Processing Systems, Volume 2. 2042\u20132050."},{"key":"e_1_3_3_19_2","volume-title":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. 55\u201364","author":"Xiong C.","unstructured":"C. Xiong, Z. Dai, and J. Callan. 2017. End-to-end neural ad-hoc ranking with kernel pooling. In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. 55\u201364."},{"key":"e_1_3_3_20_2","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems. 6297\u20136308","author":"McCann B.","unstructured":"B. McCann, J. Bradbury, C. Xiong, and R. Socher. 2017. Learned in translation: Contextualized word vectors. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 6297\u20136308."},{"key":"e_1_3_3_21_2","volume-title":"Proceedings of the 26th International Conference on World Wide Web. 1291\u20131299","author":"Mitra B.","unstructured":"B. Mitra, F. Diaz, and N. Craswell. 2017. Learning to match using local and distributed representations of text for web search. In Proceedings of the 26th International Conference on World Wide Web. 1291\u20131299."},{"key":"e_1_3_3_22_2","unstructured":"B. Mitra and N. Craswell. 2017. Neural models for information retrieval. arXiv:1705.01509. Retrieved from https:\/\/arxiv.org\/abs\/1705.01509"},{"key":"e_1_3_3_23_2","volume-title":"Proceedings of the ACM SIGIR on International Conference on Theory of Information Retrieval. 161\u2013168","author":"Macdonald C.","unstructured":"C. Macdonald and N. Tonellotto. 2020. Declarative experimentation in information retrieval using PyTerrier. In Proceedings of the ACM SIGIR on International Conference on Theory of Information Retrieval. 161\u2013168."},{"key":"e_1_3_3_24_2","volume-title":"PARADE: Passage representation aggregation for document reranking. arXiv:2008.09093.","author":"Li C.","year":"2020","unstructured":"C. Li, A. Yates, S. MacAvaney, B. He, and Y. Sun. 2020. PARADE: Passage representation aggregation for document reranking. arXiv:2008.09093. Retrieved from https:\/\/arxiv.org\/abs\/2008.09093"},{"key":"e_1_3_3_25_2","volume-title":"Australasian Database Conference. Springer, Cham, 205\u2013216","author":"Luo C.","unstructured":"C. Luo, Y. Zheng, J. Mao, Y. Liu, M. Zhang, and S. Ma. 2017. Training deep ranking model with weak relevance labels. In Australasian Database Conference. Springer, Cham, 205\u2013216."},{"key":"e_1_3_3_26_2","unstructured":"C. Raffel N. Shazeer A. Roberts K. Lee S. Narang M. Matena Y. Zhou W. Li and P. J. Liu. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv:1910.10683. Retrieved from https:\/\/arxiv.org\/abs\/1910.10683"},{"key":"e_1_3_3_27_2","doi-asserted-by":"crossref","unstructured":"D. Cer Y. Yang S. Kong N. Hua N. Limtiaco R. S John N. Constant M. Guajardo-Cespedes S. Yuan C. Tar Y.-H. Sung B. Strope and R. Kurzweil. 2018. Universal sentence encoder. arXiv: 1803.11175. Retrieved from https:\/\/arxiv.org\/abs\/1803.11175","DOI":"10.18653\/v1\/D18-2029"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670"},{"key":"e_1_3_3_30_2","doi-asserted-by":"crossref","unstructured":"E. Alsentzer J. R. Murphy W. Boag W. H. Weng D. Jin T. Naumann and M. McDermott. 2019. Publicly available clinical BERT embeddings. arXiv:1904.03323. Retrieved from https:\/\/arxiv.org\/abs\/1904.03323","DOI":"10.18653\/v1\/W19-1909"},{"key":"e_1_3_3_31_2","doi-asserted-by":"crossref","unstructured":"E. Kamalloo X. Zhang O. Ogundepo N. Thakur D. Alfonso-Hermelo M. Rezagholizadeh and J. Lin. 2023. Evaluating embedding APIs for information retrieval. arXiv:2305.06300. Retrieved from https:\/\/arxiv.org\/abs\/2305.06300","DOI":"10.18653\/v1\/2023.acl-industry.50"},{"key":"e_1_3_3_32_2","volume-title":"Overview of the TREC 2004 robust track. In Proceedings of the 23rd Text REtrieval Conference (TREC \u201904)","author":"Voorhees E. M.","year":"2004","unstructured":"E. M. Voorhees. 2004. Overview of the TREC 2004 robust track. In Proceedings of the 23rd Text REtrieval Conference (TREC \u201904). 52\u201369."},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/361219.361220"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/182.358466"},{"key":"e_1_3_3_36_2","unstructured":"H. C. Yu C. Xiong and J. Callan. 2021. Improving query representations for dense retrieval with pseudo-relevance feedback. arXiv:2108.13454. Retrieved from https:\/\/arxiv.org\/abs\/2108.13454"},{"key":"e_1_3_3_37_2","doi-asserted-by":"crossref","unstructured":"H. Gharagozlou J. Mohammadzadeh A. Bastanfard and S. S. Ghidary. 2022. RLAS-BIABC: A reinforcement learning-based answer selection using the BERT model boosted by an improved ABC algorithm. Comput. Intell. Neurosci. (2022).","DOI":"10.1155\/2022\/7839840"},{"key":"e_1_3_3_38_2","unstructured":"H. Sch\u00fctze C. D. Manning and P. Raghavan. 2008. Introduction to Information Retrieval. Cambridge University Press Cambridge UK."},{"key":"e_1_3_3_39_2","volume-title":"Martinet et\u00a0al","author":"Touvron H.","year":"2023","unstructured":"H. Touvron, T. Lavril, G. Izacard, X. Martinet et\u00a0al. 2023. Llama: Open and efficient foundation language models. arXiv:2302.13971. Retrieved from https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_3_40_2","volume-title":"Albert et\u00a0al","author":"Touvron H.","year":"2023","unstructured":"H. Touvron, L. Martin, K. Stone, P. Albert et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv:2307.09288. Retrieved from https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_3_41_2","volume-title":"Proceedings of the ACM SIGIR International Conference on Theory of Information Retrieval. 147\u2013154","author":"Zamani H.","unstructured":"H. Zamani, and W. B. Croft. 2018. On the theory of weak supervision for information retrieval. In Proceedings of the ACM SIGIR International Conference on Theory of Information Retrieval. 147\u2013154."},{"key":"e_1_3_3_42_2","volume-title":"Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. 105\u2013114","author":"Zamani H.","unstructured":"H. Zamani, W. B. Croft, and J. S. Culpepper. 2018. Neural query performance prediction using weak supervision from multiple signals. In Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. 105\u2013114."},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_3_44_2","volume-title":"Proceedings of the 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks. 326\u2013336","author":"Jahan I.","year":"2022","unstructured":"I. Jahan, M. T. R. Laskar, C. Peng, J. X. Huang. 2022. Evaluation of ChatGPT on biomedical tasks: A zero-shot comparison with fine-tuned generative transformers. In Proceedings of the 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks. 326\u2013336."},{"key":"e_1_3_3_45_2","volume-title":"Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171\u20134186","author":"Devlin J.","unstructured":"J. Devlin, M. W Chang, K. Lee, and K. Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171\u20134186."},{"key":"e_1_3_3_46_2","volume-title":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. 1297\u20131300","author":"Guo J.","unstructured":"J. Guo, Y. Fan, X. Ji, and X. Cheng. 2019. Matchzoo: A learning, practicing, and developing system for neural text matching. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. 1297\u20131300."},{"key":"e_1_3_3_47_2","volume-title":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management. 55\u201364","author":"Guo J.","unstructured":"J. Guo, Y. Fan, Q. Ai, and W. B. Croft. 2016. A deep relevance matching model for ad-hoc retrieval. In Proceedings of the 25th ACM International on Conference on Information and Knowledge Management. 55\u201364."},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102067"},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"e_1_3_3_50_2","volume-title":"Pyserini: An easy-to-use python toolkit to support replicable ir research with sparse and dense representations. arXiv:2102.10073.","author":"Lin J.","year":"2021","unstructured":"J. Lin, X. Ma, S. C. Lin, J. H. Yang, R. Pradeep, and R. Nogueira. 2021. Pyserini: An easy-to-use python toolkit to support replicable ir research with sparse and dense representations. arXiv:2102.10073. Retrieved from https:\/\/arxiv.org\/abs\/2102.10073"},{"key":"e_1_3_3_51_2","volume-title":"Proceedings of the 14th ACM International Conference on Web Search and Data Mining.","author":"Lin J.","unstructured":"J. Lin, R. Nogueira, and A. Yates. 2021. Pretrained transformers for text ranking: BERT and beyond. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining."},{"key":"e_1_3_3_52_2","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP \u201914)","author":"Pennington J.","unstructured":"J. Pennington, R. Socher, and C. D. Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP \u201914)."},{"key":"e_1_3_3_53_2","volume-title":"Proceedings of the 23rd Text REtrieval Conference (TREC \u201914)","author":"Lin J.","unstructured":"J. Lin, M. Efron, Y. Wang, and G. Sherman. 2014. Overview of the TREC-2014 microblog track. In Proceedings of the 23rd Text REtrieval Conference (TREC \u201914)."},{"key":"e_1_3_3_54_2","volume-title":"Proceedings of the 21st Annual International ACM SIGIR Conference","author":"Ponte J.","year":"1998","unstructured":"J. Ponte and W. B. Croft. 1998. A language modeling approach to information retrieval. In Proceedings of the 21st Annual International ACM SIGIR Conference (1998), 275\u2013281."},{"key":"e_1_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026028229881"},{"key":"e_1_3_3_56_2","volume-title":"Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval.","author":"Huang J. X.","unstructured":"J. X. Huang and Q. Hu. 2009. A bayesian learning approach to promoting diversity in ranking for biomedical information retrieval. In Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval."},{"key":"e_1_3_3_57_2","doi-asserted-by":"crossref","unstructured":"J. X. Huang M. Zhong and L. Si. 2005. York University at TREC 2005: Genomics Track. In TREC. 2005.","DOI":"10.6028\/NIST.SP.500-266.genomics-yorku.huang"},{"key":"e_1_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2012.08.002"},{"key":"e_1_3_3_59_2","unstructured":"J. Zhan J. Mao Y. Liu M. Zhang and S. Ma. 2020. RepBERT: Contextualized text embeddings for first-stage retrieval. 2020. arXiv:2006.15498. Retrieved from https:\/\/arxiv.org\/abs\/2006.15498"},{"key":"e_1_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/2590988"},{"key":"e_1_3_3_61_2","volume-title":"Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval.","author":"Zhao J.","unstructured":"J. Zhao, J. X. Huang, and B. He. 2011. CRTER: Using cross terms to enhance probabilistic information retrieval. In Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval."},{"key":"e_1_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-017-9321-y"},{"key":"e_1_3_3_63_2","volume-title":"Proceedings of International Conference on Learning Representations (ICLR \u201920)","author":"Clark K.","unstructured":"K. Clark, M. T. Luong, Q. V. Le, and C. D. Manning. 2020. ELECTRA: Pre-training text encoders as discriminators rather than generatorsg. In Proceedings of International Conference on Learning Representations (ICLR \u201920)."},{"key":"e_1_3_3_64_2","volume-title":"Proceedings of the 11th ACM International Conference on Web Search and Data Mining. 279\u2013287","author":"Hui K.","unstructured":"K. Hui, A. Yates, K. Berberich, and G. Melo. 2018. Co-PACRR: A context-aware neural IR model for ad-hoc retrieval. In Proceedings of the 11th ACM International Conference on Web Search and Data Mining. 279\u2013287."},{"key":"e_1_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534965"},{"key":"e_1_3_3_66_2","volume-title":"Proceedings of The Web Conference. 474\u2013485","author":"Zhang K.","unstructured":"K. Zhang, C. Xiong, Z. Liu, and Z. Liu. 2020. Selective weak supervision for neural information retrieval. In Proceedings of The Web Conference. 474\u2013485."},{"key":"e_1_3_3_67_2","volume-title":"Proceedings of the Text REtrieval Conference (TREC \u201917)","author":"Dietz L.","unstructured":"L. Dietz, M. Verma, F. Radlinski, and N. Craswell. 2017. TREC complex answer retrieval overview. In Proceedings of the Text REtrieval Conference (TREC \u201917)."},{"key":"e_1_3_3_68_2","unstructured":"L. Liu M. Li J. Lin S. Riedel and P. Stenetorp. 2022. Query expansion Using contextual clue sampling with language models. arXiv:2210.07093. Retrieved from https:\/\/arxiv.org\/abs\/2210.07093"},{"key":"e_1_3_3_69_2","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence. 2793\u20132799","author":"Pang L.","unstructured":"L. Pang, Y. Lan, J. Guo, J. Xu, S. Wan, and X. Cheng. 2016. Text matching as image recognition. In Proceedings of the AAAI Conference on Artificial Intelligence. 2793\u20132799."},{"key":"e_1_3_3_70_2","unstructured":"L. Xiong C. Xiong Y. Li K. Tang and J. Liu. 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv:2007.00808. Retrieved from https:\/\/arxiv.org\/abs\/2007.000808"},{"key":"e_1_3_3_71_2","unstructured":"M. Dehghani A. Severyn S. Rothe and J. Kamps. 2017. Learning to learn from weak supervision by full supervision. arXiv:1711.11383. Retrieved from https:\/\/arxiv.org\/abs\/1711.11383"},{"key":"e_1_3_3_72_2","first-page":"12792","article-title":"Cogltx: Applying bert to long texts","volume":"33","author":"Ding M.","year":"2020","unstructured":"M. Ding, C. Zhou, H. Yang, and J. Tang. 2020. Cogltx: Applying bert to long texts. In Advances in Neural Information Processing Systems, Vol. 33, 12792\u201312804.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_73_2","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence. 10672\u201310680","author":"Gaur M.","unstructured":"M. Gaur, K. Gunaratna, V. Srinivasan, and H. Jin. 2022. Iseeq: Information seeking question generation using dynamic meta-information retrieval and knowledge graphs. In Proceedings of the AAAI Conference on Artificial Intelligence. 10672\u201310680."},{"key":"e_1_3_3_74_2","volume-title":"Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2227\u20132237","author":"Peters M. E.","unstructured":"M. E. Peters, M. Neumann, M. Iyyer, M. Gardner, C. Clark, K. Lee, and L. Zettlemoyer. 2018. Deep contextualized word representation. In Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2227\u20132237."},{"key":"e_1_3_3_75_2","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2207\u20132211","author":"Li M.","unstructured":"M. Li and E. Gaussier. 2021. KeyBLD: Selecting key blocks with local pre-ranking for long document information retrieval. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2207\u20132211."},{"key":"e_1_3_3_76_2","volume-title":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval.","author":"Li M.","unstructured":"M. Li and E. Gaussier. 2022. BERT-based dense intra-ranking and contextualized late interaction via multi-task learning for long document retrieval. In Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval."},{"key":"e_1_3_3_77_2","volume-title":"Proceedings of the ACM SIGIR Forum. 63\u201370","author":"Lupu M.","unstructured":"M. Lupu, J. X. Huang, J. Zhu, and J. Tait. 2009. TREC-CHEM: Large scale chemical information retrieval evaluation at TREC. In Proceedings of the ACM SIGIR Forum. 63\u201370."},{"key":"e_1_3_3_78_2","volume-title":"Overview of the TREC 2009 chemical IR track. In Proceedings of the Text REtrieval Conference (TREC \u201909)","author":"Lupu M.","unstructured":"M. Lupu, J. X. Huang, J. Zhu, and J. Tait. 2009. Overview of the TREC 2009 chemical IR track. In Proceedings of the Text REtrieval Conference (TREC \u201909)."},{"key":"e_1_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102734"},{"key":"e_1_3_3_80_2","volume-title":"SPRF: A semantic pseudo-relevance feedback enhancement for information retrieval via ConceptNet. Knowl.-Bas. Syst. 274, 110602","author":"Pan M.","year":"2023","unstructured":"M. Pan, Q. Pei, Y. Liu, T. Li, E. A. Huang, J. Wang, and J. X. Huang. 2023. SPRF: A semantic pseudo-relevance feedback enhancement for information retrieval via ConceptNet. Knowl.-Bas. Syst. 274, 110602 (2023)."},{"key":"e_1_3_3_81_2","doi-asserted-by":"crossref","unstructured":"M. T. R. Laskar M. S. Bari M. Rahman M. A. H. Bhuiyan S. Joty and J. X. Huang. 2023. A systematic study and comprehensive evaluation of ChatGPT on benchmark datasets. In Findings of the Association for Computational Linguistics. 431\u2013469.","DOI":"10.18653\/v1\/2023.findings-acl.29"},{"key":"e_1_3_3_82_2","volume-title":"Proceedings of the 12th Language Resources and Evaluation Conference.","author":"Laskar M. T. R.","unstructured":"M. T. R. Laskar, J. X. Huang, and E. Hoque. 2020. Contextualized embeddings-based transformer encoder for sentence similarity modeling in answer selection task. In Proceedings of the 12th Language Resources and Evaluation Conference."},{"key":"e_1_3_3_83_2","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00434"},{"key":"e_1_3_3_84_2","volume-title":"Proceedings of the 28th International Conference on Computational Linguistics. 5647\u20135654","author":"Laskar M. T. R.","unstructured":"M. T. R. Laskar, E. Hoque, and J. X. Huang. 2020. WSL-DS: Weakly supervised learning with distant supervision for query-focused multi-document abstractive summarization. In Proceedings of the 28th International Conference on Computational Linguistics. 5647\u20135654."},{"key":"e_1_3_3_85_2","volume-title":"Proceedings of the Text REtrieval Conference (TREC \u201919)","author":"Yan M.","unstructured":"M. Yan, C. Li, C. Wu, B. Bi, W. Wang, J. Xia, and L. Si. 2019. IDST at TREC 2019 deep learning track: Deep cascade ranking with generation-based document expansion and pre-trained language modeling. In Proceedings of the Text REtrieval Conference (TREC \u201919)."},{"key":"e_1_3_3_86_2","doi-asserted-by":"crossref","unstructured":"N. Reimers and I. Gurevych. 2019. Sentence-BERT: Sentence embeddings using siamese BERT-networks. arXiv:1908.10084. Retrieved from https:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_3_87_2","volume-title":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 39\u201348","author":"Khattab O.","unstructured":"O. Khattab and M. Zaharia. 2020. ColBERT: Efficient and effective passage search via contextualized late interaction over BERT. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 39\u201348."},{"key":"e_1_3_3_88_2","first-page":"13","article-title":"GPT-4 technical report. arXiv:2303.08774","volume":"2","author":"R.","year":"2023","unstructured":"R. OpenAI. 2023. GPT-4 technical report. arXiv:2303.08774. View in Article, 2, 13.","journal-title":"View in Article"},{"key":"e_1_3_3_89_2","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis P.","year":"2020","unstructured":"P. Lewis, E. Perez, A. Piktus, F. Petroni et\u00a0al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. In Advances in Neural Information Processing Systems, Vol. 33, 9459\u20139474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_90_2","volume-title":"Proceedings of the 22nd ACM International Conference on Information & Knowledge Management. 2333\u20132338","author":"Huang P. S.","unstructured":"P. S. Huang, X. He, J. Gao, L. Deng, A. Acero, and L. Heck. 2013. Learning deep structured semantic models for web search using clickthrough data. In Proceedings of the 22nd ACM International Conference on Information & Knowledge Management. 2333\u20132338."},{"key":"e_1_3_3_91_2","unstructured":"P. Shi and J. Lin. 2019. Cross-lingual relevance transfer for document retrieval. arXiv:1911.02989. Retrieved from https:\/\/arxiv.org\/abs\/1911.02989"},{"key":"e_1_3_3_92_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09765-w"},{"key":"e_1_3_3_93_2","unstructured":"P. Xu X. Ma R. Nallapati and B. Xiang. 2019. Passage ranking with weak supervision. arXiv:1905.05910. Retrieved from https:\/\/arxiv.org\/abs\/1905.05910"},{"key":"e_1_3_3_94_2","volume-title":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1253\u20131256","author":"Yang P.","unstructured":"P. Yang, H. Fang, and J. Lin. 2017. 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. 1253\u20131256."},{"key":"e_1_3_3_95_2","volume-title":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval.","author":"Chen Q.","unstructured":"Q. Chen, Q. Hu, J. X. Huang, L. He, and W. An. 2017. Enhancing recurrent neural networks with positional attention for question answering. 2017. In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval."},{"key":"e_1_3_3_96_2","volume-title":"Lepikhin et\u00a0al","author":"Anil R.","year":"2023","unstructured":"R. Anil, A. M. Dai, O. Firat, M. Johnson, D. Lepikhin et\u00a0al. 2023. Palm 2 technical report. arXiv:2305.10403. Retrieved from https:\/\/arxiv.org\/abs\/2305.10403"},{"key":"e_1_3_3_97_2","volume-title":"European Conference on Information Retrieval. Springer, Cham, 297\u2013304","author":"Padaki R.","unstructured":"R. Padaki, Z. Dai, and J. Callan. 2020. Rethinking query expansion for BERT reranking. In European Conference on Information Retrieval. Springer, Cham, 297\u2013304."},{"key":"e_1_3_3_98_2","unstructured":"R. Nogueira J. Lin and A. I. Epistemic. 2019. From doc2query to docTTTTTquery. Online preprint 6 2."},{"key":"e_1_3_3_99_2","unstructured":"R. Nogueira and K. Cho. 2019. Passage Re-ranking with BERT. arXiv:1901.04085. Retrieved from https:\/\/arxiv.org\/abs\/1901.04085"},{"key":"e_1_3_3_100_2","unstructured":"R. Nogueira W. Yang K. Cho and J. Lin. 2019. Multi-stage document ranking with BERT. arXiv:1904.08375. Retrieved from https:\/\/arxiv.org\/abs\/1904.08375"},{"key":"e_1_3_3_101_2","unstructured":"R. Nogueira W. Yang J. Lin and K. Cho. 2019. Document expansion by query prediction. arXiv:1904.08375. Retrieved from https:\/\/arxiv.org\/abs\/1904.08375"},{"key":"e_1_3_3_102_2","unstructured":"R. Sennrich H. Barry and B. Alexandra. 2015. Neural machine translation of rare words with subword units. arXiv:1508.07909. Retrieved from https:\/\/arxiv.org\/abs\/1508.07909"},{"key":"e_1_3_3_103_2","doi-asserted-by":"crossref","unstructured":"R. Zhu X. Tu and J. X. Huang. 2020. Deep learning on information retrieval and its applications. In Deep Learning for Data Analytics. Academic Press San Diego CA 125\u2013153.","DOI":"10.1016\/B978-0-12-819764-6.00008-9"},{"key":"e_1_3_3_104_2","unstructured":"S. C. Lin J. H. Yang and J. Lin. 2020. Distilling dense representations for ranking using tightly-coupled teachers. arXiv:2010.11386. Retrieved from https:\/\/arxiv.org\/abs\/2010.11386"},{"key":"e_1_3_3_105_2","doi-asserted-by":"crossref","unstructured":"S. Hofst\u00e4tter M. Zlabinger and A. Hanbury. 2019. TU Wien TREC deep learning\u201919\u2014Simple contextualization for re-ranking. arXiv:1912.01385. Retrieved from https:\/\/arxiv.org\/abs\/1912.01385","DOI":"10.6028\/NIST.SP.1250.deep-TU-Vienna"},{"key":"e_1_3_3_106_2","unstructured":"S. Hofst\u00e4tter M. Zlabinger and A. Hanbury. 2020. Interpretable & time-budget-constrained contextualization for re-ranking. arXiv:2002.01854. Retrieved from https:\/\/arxiv.org\/abs\/2002.01854"},{"key":"e_1_3_3_107_2","volume-title":"Proceedings of the 43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR \u201920). 2021","author":"Hofst\u00e4tter S.","year":"2024","unstructured":"S. Hofst\u00e4tter, H. Zamani, B. Mitra, N. Craswell, and A. Hanbury. 2020. Local self-attention over long text for efficient document retrieval. In Proceedings of the 43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR \u201920). 2021\u20132024."},{"key":"e_1_3_3_108_2","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 113\u2013122","author":"Hofst\u00e4tter S.","unstructured":"S. Hofst\u00e4tter, S. C. Lin, J. H. Yang, J. Lin, and A. Hanbury. 2021. Efficiently teaching an effective dense retriever with balanced topic aware sampling. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 113\u2013122."},{"key":"e_1_3_3_109_2","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1349\u20131358","author":"Hofst\u00e4tter S.","unstructured":"S. Hofst\u00e4tter, B. Mitra, H. Zamani, N. Craswell, and A. Hanbury. 2021. Intra-document cascading: Learning to select passages for neural document ranking. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1349\u20131358."},{"key":"e_1_3_3_110_2","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371864"},{"key":"e_1_3_3_111_2","volume-title":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 1573\u20131576","author":"MacAvaney S.","unstructured":"S. MacAvaney, F. M. Nardini, R. Perego, N. Tonellotto, N. Goharian, and O. Frieder. 2020. Expansion via prediction of importance with contextualization. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 1573\u20131576."},{"key":"e_1_3_3_112_2","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331317"},{"key":"e_1_3_3_113_2","volume-title":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 529\u2013538","author":"Macavaney S.","unstructured":"S. Macavaney, F. M. Nardini, R. Perego, N. Tonellotto, N. Goharian, and O. Frieder. 2020. Training curricula for open domain answer re-ranking. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 529\u2013538."},{"key":"e_1_3_3_114_2","volume-title":"CEQE: Contextualized embeddings for query expansion. In European Conference on Information Retrieval","author":"Naseri S.","year":"2021","unstructured":"S. Naseri, J. Dalton, A. Yates, and J. Allan. 2021. CEQE: Contextualized embeddings for query expansion. In European Conference on Information Retrieval. Springer, Cham, 467\u2013482."},{"key":"e_1_3_3_115_2","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_3_116_2","doi-asserted-by":"publisher","DOI":"10.1145\/3471158.3472233"},{"key":"e_1_3_3_117_2","volume-title":"Proceedings of the 25th International Joint Conference on Artificial Intelligence. 2922\u20132928","author":"Wan S.","unstructured":"S. Wan, Y. Lan, J. Xu, J. Guo, L. Pang, and X. Cheng. 2016. Match-SRNN: modeling the recursive matching structure with spatial RNN. In Proceedings of the 25th International Joint Conference on Artificial Intelligence. 2922\u20132928."},{"key":"e_1_3_3_118_2","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence.","author":"Wan S.","unstructured":"S. Wan, Y. Lan, J. Guo, J. Xu, L. Pang, and X. Cheng. 2016. A deep architecture for semantic matching with multiple positional sentence representations. In Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_3_119_2","doi-asserted-by":"publisher","DOI":"10.1145\/3158369"},{"key":"e_1_3_3_120_2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown T.","year":"2020","unstructured":"T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam et\u00a0al. 2020. Language models are few-shot learners. In Advances in Neural Information Processing Systems, Vol. 33, 1877\u20131901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_121_2","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2288\u20132292","author":"Formal T.","unstructured":"T. Formal, B. Piwowarski, and S. Clinchant. 2021. SPLADE: Sparse lexical and expansion model for first stage ranking. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2288\u20132292."},{"key":"e_1_3_3_122_2","unstructured":"T. Mikolov K. Chen G. Corrado and J. Dean. 2013. Efficient estimation of word representations in vector space. arXiv:1301.3781. Retrieved from https:\/\/arxiv.org\/abs\/1301.3781"},{"key":"e_1_3_3_123_2","volume-title":"Proceedings of the Workshop on Cognitive Computation: Integrating Neural and Symbolic Approaches Co-located with the 30th Annual Conference on Neural Information Processing Systems (NIPS \u201916)","author":"Nguyen T.","unstructured":"T. Nguyen, M. Rosenberg, X. Song, J. Guo, S. Tiwary, R. Majumder, and L. Deng. 2016. MS MARCO: A human generated machine reading comprehension dataset. In Proceedings of the Workshop on Cognitive Computation: Integrating Neural and Symbolic Approaches Co-located with the 30th Annual Conference on Neural Information Processing Systems (NIPS \u201916)."},{"key":"e_1_3_3_124_2","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP \u201920)","author":"Karpukhin V.","unstructured":"V. Karpukhin, B. O \\(\\breve{g}\\) uz, S. Min, P. Lewis, L. Wu, S. Edunov, D. Chen, and W. Yih. 2020. Dense passage retrieval for open-domain question answering. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP \u201920)."},{"key":"e_1_3_3_125_2","unstructured":"V. Sanh L. Debut J. Chaumond and T. Wolf. 2019. DistilBERT a distilled version of BERT: Smaller faster cheaper and lighter. arXiv:1910.01108. Retrieved from https:\/\/arxiv.org\/abs\/1910.01108"},{"key":"e_1_3_3_126_2","volume-title":"Search Engines: Information Retrieval in Practice","author":"Croft W. B.","year":"2010","unstructured":"W. B. Croft, D. Metzler, and T. Strohman. 2010. Search Engines: Information Retrieval in Practice. Addison-Wesley, Reading, MA."},{"key":"e_1_3_3_127_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.12.038"},{"key":"e_1_3_3_128_2","volume-title":"FastBERT: A self-distilling BERT with adaptive inference time","author":"Liu W.","year":"2020","unstructured":"W. Liu, P. Zhou, Z. Zhao, Z. Wang, H. Deng, and Q. Ju. FastBERT: A self-distilling BERT with adaptive inference time. 2020. arXiv:2004.02178. Retrieved from https:\/\/arxiv.org\/abs\/2004.02178"},{"key":"e_1_3_3_129_2","volume-title":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 2645\u20132652","author":"Lu W.","unstructured":"W. Lu, J. Jiao, and R. Zhang. 2020. Twinbert: Distilling knowledge to twin-structured compressed bert models for large-scale retrieval. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 2645\u20132652."},{"key":"e_1_3_3_130_2","doi-asserted-by":"crossref","unstructured":"W. Sun L. Yan X. Ma P. Ren D. Yin and Z. Ren. 2023. Is ChatGPT good at search? Investigating large language models as re-ranking agent. arXiv:2304.09542. Retrieved from https:\/\/arxiv.org\/abs\/2304.09542","DOI":"10.18653\/v1\/2023.emnlp-main.923"},{"key":"e_1_3_3_131_2","unstructured":"W. Wang B. Bi M. Yan C. Wu Z. Bao J. Xia L. Peng and Si L. 2019. StructBERT: Incorporating language structures into pre-training for deep language understanding. arXiv: 1908.04577. Retrieved from https:\/\/arxiv.org\/abs\/1908.04577"},{"key":"e_1_3_3_132_2","unstructured":"W. Yang H. Zhang and J. Lin. 2019. Simple applications of BERT for ad hoc document retrieval. arXiv: 1903.10972. Retrieved from https:\/\/arxiv.org\/abs\/1903.10972"},{"key":"e_1_3_3_133_2","doi-asserted-by":"crossref","unstructured":"X. Jiao Y. Yin L. Shang X. Jiang X. Chen L. Li F. Wang and Q. Liu. 2020. TinyBERT: Distilling BERT for natural language understanding. In Findings of the Association for Computational Linguistics: EMNLP. 4163\u20134174.","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"e_1_3_3_134_2","volume-title":"Proceedings of the ACM SIGIR International Conference on Theory of Information Retrieval. 297\u2013306","author":"Wang X.","unstructured":"X. Wang, C. Macdonald, N. Tonellotto, and I. Ounis. 2021. Pseudo-relevance feedback for multiple representation dense retrieval. In Proceedings of the ACM SIGIR International Conference on Theory of Information Retrieval. 297\u2013306."},{"key":"e_1_3_3_135_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2012.24"},{"key":"e_1_3_3_136_2","volume-title":"European Conference on Information Retrieval. Springer, Cham, 150\u2013163","author":"Zhang X.","unstructured":"X. Zhang, A. Yates, and J. Lin. 2021. Comparing score aggregation approaches for document retrieval with pretrained transformers. In European Conference on Information Retrieval. Springer, Cham, 150\u2013163."},{"key":"e_1_3_3_137_2","unstructured":"Y. Bai X. Li G. Wang C. Zhang L. Shang J. Xu Z. Wang F. Wang and Q. Liu. 2020. SparTerm: Learning term-based sparse representation for fast text retrieval. arXiv:2010.00768. Retrieved from https:\/\/arxiv.org\/abs\/2010.00768"},{"key":"e_1_3_3_138_2","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing: Findings. 657\u2013668","author":"Cui Y.","unstructured":"Y. Cui, W. Che, T. Liu, B. Qin, S. Wang, and G. Hu. 2020. Revisiting pre-trained models for Chinese natural language processing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing: Findings. 657\u2013668."},{"key":"e_1_3_3_139_2","doi-asserted-by":"publisher","unstructured":"Y. Lecun Y. Bengio and G. Hinton. 2015. Deep learning. Nature 521 7553 (2015) 436\u2013444. 10.1038\/nature14539","DOI":"10.1038\/nature14539"},{"key":"e_1_3_3_140_2","volume-title":"Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.","author":"Liu Y.","unstructured":"Y. Liu, J. X. Huang, A. An, and X. Yu. 2007. ARSA: A sentiment-aware model for predicting sales performance using blogs. In Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval."},{"key":"e_1_3_3_141_2","volume-title":"Roberta","author":"Liu Y.","year":"2019","unstructured":"Y. Liu, M. Ott, N. Goyal, J. F. Du, M. Joshi, D. Q. Chen, O. Levy, M. Lewis, Zettlemoyer L, and Stoyanov V. Roberta. 2019. A robustly optimized BERT pretraining approach. arXiv:1907.11692. Retrieved from https:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_3_142_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00369"},{"key":"e_1_3_3_143_2","unstructured":"Y. Wu M. Schuster Z. Chen Q. V.Le and M. Norouzi. 2016. Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv:1609.08144. Retrieved from https:\/\/arxiv.org\/abs\/1609.08144"},{"key":"e_1_3_3_144_2","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP \u201919)","author":"Yilmaz Z. A.","unstructured":"Z. A. Yilmaz, S. Wang, W. Yang, H. Zhang, and J. Lin. 2019. Applying BERT to document retrieval with birch. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP \u201919). 19\u201324."},{"key":"e_1_3_3_145_2","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP \u201919)","author":"Yilmaz Z. A.","unstructured":"Z. A. Yilmaz, W. Yang, H. Zhang, and J. Lin. 2019. Cross-domain sentence modeling for relevance transfer with BERT. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP \u201919)."},{"key":"e_1_3_3_146_2","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2978\u20132988","author":"Dai Z.","unstructured":"Z. Dai, Z. Yang, Y. Yang, J. Carbonell, Q. Le, and R. Salakhutdinov. 2019. Transformer-XL: Attention language models beyond a fixed-length comtext. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2978\u20132988."},{"key":"e_1_3_3_147_2","volume-title":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. 985\u2013988","author":"Dai Z.","unstructured":"Z. Dai and J. Callan. 2019. Deeper text understanding for IR with contextual neural language modeling. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. 985\u2013988."},{"key":"e_1_3_3_148_2","volume-title":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 1533\u20131536","author":"Dai Z.","unstructured":"Z. Dai and J. Callan. 2020. Context-aware passage term weighting for first stage retrieval. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 1533\u20131536."},{"key":"e_1_3_3_149_2","volume-title":"Proceedings of the Web Conference. 1897\u20131907","author":"Dai Z.","unstructured":"Z. Dai and J. Callan. 2020. Context-aware document term weighting for ad-hoc search. In Proceedings of the Web Conference. 1897\u20131907."},{"key":"e_1_3_3_150_2","volume-title":"Proceedings of the 11th ACM International Conference on Web Search and Data Mining. 126\u2013134","author":"Dai Z.","unstructured":"Z. Dai, C. Xiong, J. Callan, and Z. Liu. 2018. Convolutional neural networks for soft-matching n-grams in ad-hoc search. In Proceedings of the 11th ACM International Conference on Web Search and Data Mining. 126\u2013134."},{"key":"e_1_3_3_151_2","unstructured":"Z. Lan M. Chen S. Goodman K. Gimpel P. Sharma and R. Soricut. 2019. AlBERT: A lite BERT for self-supervised learning of language representations. arXiv:1909.11942. Retrieved from https:\/\/arxiv.org\/abs\/1909.11942"},{"key":"e_1_3_3_152_2","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2531\u20132535","author":"Liu Z.","unstructured":"Z. Liu, K. Zhang, C. Xiong, Z. Liu, and M. Sun. 2021. OpenMatch: An open source library for Neu-IR research. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2531\u20132535."},{"key":"e_1_3_3_153_2","volume-title":"Wang et\u00a0al","author":"Qin Z.","year":"2023","unstructured":"Z. Qin, R. Jagerman, K. Hui, H. Zhuang, J. Wu, J. Shen, T. Liu, J. Liu, D. Metzler, X. Wang et\u00a0al. 2023. Large language models are effective text rankers with pairwise ranking prompting. arXiv:2306.17563. Retrieved from https:\/\/arxiv.org\/abs\/2306.17563"},{"key":"e_1_3_3_154_2","volume-title":"Proceedings of the Web Conference. 2421\u20132431","author":"Wu Z.","unstructured":"Z. Wu, J. Mao, Y. Liu, J. Zhan, Y. Zheng, M. Zhang, and S. Ma. 2020. Leveraging passage-level cumulative gain for document ranking. In Proceedings of the Web Conference. 2421\u20132431."},{"key":"e_1_3_3_155_2","first-page":"5753","article-title":"XLNET: Generalized autoregressive pretraining for language understanding","volume":"32","author":"Yang Z.","year":"2019","unstructured":"Z. Yang, Z. Dai, Y. Yang, and J. Carbonell. 2019. XLNET: Generalized autoregressive pretraining for language understanding. In Proceedings of Advances in Neural Information Processing Systems, Vol. 32, 5753\u20135763.","journal-title":"Proceedings of Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_156_2","doi-asserted-by":"publisher","DOI":"10.1002\/asi.21501"},{"key":"e_1_3_3_157_2","doi-asserted-by":"crossref","unstructured":"Z. Zheng K. Hui B. He X. Han L. Sun and A. Yates. 2020. BERT-QE: Contextualized query expansion for document re-ranking. arXiv:2009.07288. Retrieved from http:\/\/arxiv.org\/abs\/2009.07258","DOI":"10.18653\/v1\/2020.findings-emnlp.424"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3648471","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3648471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:19Z","timestamp":1750287019000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3648471"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,9]]},"references-count":155,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7,31]]}},"alternative-id":["10.1145\/3648471"],"URL":"https:\/\/doi.org\/10.1145\/3648471","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,9]]},"assertion":[{"value":"2021-07-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-31","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}