{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:12:52Z","timestamp":1755839572030,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591956","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"1848-1852","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Benchmarking Middle-Trained Language Models for Neural Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9837-5358","authenticated-orcid":false,"given":"Herv\u00e9","family":"D\u00e9jean","sequence":"first","affiliation":[{"name":"Naver Labs Europe, Meylan, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2367-8837","authenticated-orcid":false,"given":"Stephane","family":"Clinchant","sequence":"additional","affiliation":[{"name":"Naver Labs Europe, Meylan, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7754-6656","authenticated-orcid":false,"given":"Carlos","family":"Lassance","sequence":"additional","affiliation":[{"name":"Naver Labs Europe, Meylan, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2383-4557","authenticated-orcid":false,"given":"Simon","family":"Lupart","sequence":"additional","affiliation":[{"name":"Naver Labs Europe, Meylan, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6363-9553","authenticated-orcid":false,"given":"Thibault","family":"Formal","sequence":"additional","affiliation":[{"name":"Naver Labs Europe, Meylan, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.403"},{"volume-title":"ECIR (2) (Lecture Notes in Computer Science","author":"Bassani Elias","key":"e_1_3_2_1_2_1","unstructured":"Elias Bassani. 2022. ranx: A Blazing-Fast Python Library for Ranking Evaluation and Comparison. In ECIR (2) (Lecture Notes in Computer Science, Vol. 13186). Springer, 259--264."},{"key":"e_1_3_2_1_3_1","volume-title":"BMJ","volume":"310","author":"Bland J. M.","year":"1995","unstructured":"J. M. Bland and D. G. Altman. 1995. Multiple significance tests: the Bonferroni method. BMJ, Vol. 310, 6973 (Jan. 1995), 170. http:\/\/bmj.bmjjournals.com\/cgi\/content\/full\/310\/6973\/170"},{"key":"e_1_3_2_1_4_1","volume-title":"Pre-training Tasks for Embedding-based Large-scale Retrieval. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rkg-mA4FDr","author":"Chang Wei-Cheng","year":"2020","unstructured":"Wei-Cheng Chang, Felix X. Yu, Yin-Wen Chang, Yiming Yang, and Sanjiv Kumar. 2020. Pre-training Tasks for Embedding-based Large-scale Retrieval. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rkg-mA4FDr"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531857"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.05720"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.75"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.203"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3486250"},{"key":"e_1_3_2_1_11_1","volume-title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation. arxiv","author":"Sebastian","year":"2010","unstructured":"Sebastian Hofst\"atter, Sophia Althammer, Michael Schr\u00f6der, Mete Sertkan, and Allan Hanbury. 2020. Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation. arxiv: 2010.02666 [cs.IR]"},{"key":"e_1_3_2_1_12_1","volume-title":"Proc. of SIGIR.","author":"Sebastian","year":"2021","unstructured":"Sebastian Hofst\"atter, Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin, and Allan Hanbury. 2021. Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling. In Proc. of SIGIR."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2209.14389"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531833"},{"volume-title":"Advances in Information Retrieval","author":"Lassance Carlos","key":"e_1_3_2_1_16_1","unstructured":"Carlos Lassance, Herv\u00e9 Dejean, and St\u00e9phane Clinchant. 2023 a. An Experimental Study on Pretraining Transformers from Scratch for IR. In Advances in Information Retrieval, Jaap Kamps, Lorraine Goeuriot, Fabio Crestani, Maria Maistro, Hideo Joho, Brian Davis, Cathal Gurrin, Udo Kruschwitz, and Annalina Caputo (Eds.). Springer Nature Switzerland, Cham, 504--520."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Carlos Lassance Herv\u00e9 D\u00e9jean and St\u00e9phane Clinchant. 2023 b. An Experimental Study on Pretraining Transformers from Scratch for IR. https:\/\/doi.org\/10.48550\/ARXIV.2301.10444","DOI":"10.48550\/ARXIV.2301.10444"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.repl4nlp-1.17"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Zheng Liu and Yingxia Shao. 2022. RetroMAE: Pre-training Retrieval-oriented Transformers via Masked Auto-Encoder. https:\/\/doi.org\/10.48550\/arXiv.2205.12035 arXiv:2205.12035 [cs].","DOI":"10.48550\/arXiv.2205.12035"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462869"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441777"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482286"},{"key":"e_1_3_2_1_23_1","volume-title":"MS MARCO: A human generated machine reading comprehension dataset. In CoCo@ NIPs.","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A human generated machine reading comprehension dataset. In CoCo@ NIPs."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","unstructured":"Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage Re-ranking with BERT. https:\/\/doi.org\/10.48550\/ARXIV.1901.04085","DOI":"10.48550\/ARXIV.1901.04085"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Keshav Santhanam Omar Khattab Jon Saad-Falcon Christopher Potts and Matei Zaharia. 2021. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. arxiv: 2112.01488 [cs.IR]","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","unstructured":"Tao Shen Xiubo Geng Chongyang Tao Can Xu Xiaolong Huang Binxing Jiao Linjun Yang and Daxin Jiang. 2022. LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval. https:\/\/doi.org\/10.48550\/arXiv.2208.14754 arXiv:2208.14754 [cs].","DOI":"10.48550\/arXiv.2208.14754"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_28_1","volume-title":"Sharan Narang, Dani Yogatama, Ashish Vaswani, and Donald Metzler.","author":"Tay Yi","year":"2022","unstructured":"Yi Tay, Mostafa Dehghani, Jinfeng Rao, William Fedus, Samira Abnar, Hyung Won Chung, Sharan Narang, Dani Yogatama, Ashish Vaswani, and Donald Metzler. 2022. Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers. ArXiv, Vol. abs\/2109.10686 (2022)."},{"key":"e_1_3_2_1_29_1","volume-title":"BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. https:\/\/openreview.net\/forum?id=wCu6T5xFjeJ","author":"Thakur Nandan","year":"2022","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2022. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. https:\/\/openreview.net\/forum?id=wCu6T5xFjeJ"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Nicola Tonellotto. 2022. Lecture Notes on Neural Information Retrieval. https:\/\/doi.org\/10.48550\/ARXIV.2207.13443","DOI":"10.48550\/ARXIV.2207.13443"},{"key":"e_1_3_2_1_31_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Taipei Taiwan","acronym":"SIGIR '23"},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591956","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591956","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:38:08Z","timestamp":1750178288000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591956"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":32,"alternative-id":["10.1145\/3539618.3591956","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591956","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}