{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:16:34Z","timestamp":1784178994762,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":40,"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"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591916","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"2552-2561","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Reproducibility, Replicability, and Insights into Dense Multi-Representation Retrieval Models: from ColBERT to Col*"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5151-2773","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"first","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3143-279X","authenticated-orcid":false,"given":"Craig","family":"Macdonald","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7427-1001","authenticated-orcid":false,"given":"Nicola","family":"Tonellotto","sequence":"additional","affiliation":[{"name":"University of Pisa, Pisa, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4701-3223","authenticated-orcid":false,"given":"Iadh","family":"Ounis","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jo Kristian Bergum. 2021. Pretrained Transformer Language Models for Search - part 4. https:\/\/blog.vespa.ai\/pretrained-transformer-language-models-for-search-part-4\/"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.414"},{"key":"e_1_3_2_1_3_1","volume-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators. In Proceddings of ICLR.","author":"Clark Kevin","year":"2020","unstructured":"Kevin Clark, Minh-Thang Luong, Quoc V Le, and Christopher D Manning. 2020. ELECTRA: Pre-training text encoders as discriminators rather than generators. In Proceddings of ICLR."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of ACL. 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of ACL. 4171--4186."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72240-1_23"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99739-7_14"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28238-6_31"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.119"},{"key":"e_1_3_2_1_9_1","unstructured":"Sebastian Hofst\u00e4tter Sophia Althammer Michael Schr\u00f6der Mete Sertkan and Allan Hanbury. 2020. Improving efficient neural ranking models with cross-architecture knowledge distillation. In arXiv preprint arXiv:2010.02666."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462891"},{"key":"e_1_3_2_1_11_1","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom B Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361."},{"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":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"e_1_3_2_1_15_1","volume-title":"ALBERT: A lite BERT for self-supervised learning of language representations. In Proceddings of ICLR.","author":"Lan Zhenzhong","year":"2020","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A lite BERT for self-supervised learning of language representations. In Proceddings of ICLR."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531835"},{"key":"e_1_3_2_1_17_1","volume-title":"How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval. arXiv preprint arXiv:2302.07452","author":"Lin Sheng-Chieh","year":"2023","unstructured":"Sheng-Chieh Lin, Akari Asai, Minghan Li, Barlas Oguz, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, and Xilun Chen. 2023. How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval. arXiv preprint arXiv:2302.07452 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Distilling dense representations for ranking using tightly-coupled teachers. arXiv preprint arXiv:2010.11386","author":"Lin Sheng-Chieh","year":"2020","unstructured":"Sheng-Chieh Lin, Jheng-Hong Yang, and Jimmy Lin. 2020. Distilling dense representations for ranking using tightly-coupled teachers. arXiv preprint arXiv:2010.11386 (2020)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.repl4nlp-1.17"},{"key":"e_1_3_2_1_20_1","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2020. RoBERTa: A Robustly Optimized BERT Pretraining Approach. In Proceddings of ICLR."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557231"},{"key":"e_1_3_2_1_22_1","volume-title":"On Single and Multiple Representations in Dense Passage Retrieval. IIR 2021 Workshop","author":"Macdonald Craig","year":"2021","unstructured":"Craig Macdonald, Nicola Tonellotto, and Iadh Ounis. 2021. On Single and Multiple Representations in Dense Passage Retrieval. IIR 2021 Workshop (2021)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Suraj Nair Eugene Yang Dawn Lawrie Kevin Duh Paul McNamee Kenton Murray James Mayfield and Douglas W Oard. 2022. Transfer learning approaches for building cross-language dense retrieval models. In roceddings of ECIR. 382--396.","DOI":"10.1007\/978-3-030-99736-6_26"},{"key":"e_1_3_2_1_24_1","unstructured":"Association of Computing Machinery. 2020. Artifact Review and Badging. https:\/\/www.acm.org\/publications\/policies\/artifact-review-and-badging-current."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"e_1_3_2_1_26_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners."},{"key":"e_1_3_2_1_27_1","volume-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research (2020), 1--67."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of Workshop on African Natural Language Processing.","author":"Rajab Jenalea","year":"2022","unstructured":"Jenalea Rajab. 2022. Effect of Tokenisation Strategies for Low-Resourced Southern African Languages. In Proceedings of Workshop on African Natural Language Processing."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of NAACL.","author":"Santhanam Keshav","year":"2021","unstructured":"Keshav Santhanam, Omar Khattab, Jon Saad-Falcon, Christopher Potts, and Matei Zaharia. 2021. ColBERTv2: Effective and efficient retrieval via lightweight late interaction. In Proceedings of NAACL."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531766"},{"key":"e_1_3_2_1_31_1","volume-title":"Japanese and korean voice search","author":"Schuster Mike","unstructured":"Mike Schuster and Kaisuke Nakajima. 2012. Japanese and korean voice search. In Proceddings of ICASSP. IEEE, 5149--5152."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_3_2_1_33_1","volume-title":"Furkan cS ahinucc, and Oguzhan Ozcelik.","author":"Toraman Cagri","year":"2022","unstructured":"Cagri Toraman, Eyup Halit Yilmaz, Furkan cS ahinucc, and Oguzhan Ozcelik. 2022. Impact of Tokenization on Language Models: An Analysis for Turkish. arXiv preprint arXiv:2204.08832 (2022)."},{"key":"e_1_3_2_1_34_1","first-page":"5776","article-title":"MiniLM: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume":"33","author":"Wang Wenhui","year":"2020","unstructured":"Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. MiniLM: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. In Proceddings of NeurIPS, Vol. 33. 5776--5788.","journal-title":"Proceddings of NeurIPS"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531721"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103026"},{"key":"e_1_3_2_1_37_1","volume-title":"ColBERT-PRF: Semantic Pseudo-Relevance Feedback for Dense Passage and Document Retrieval. ACM Transactions on the Web","author":"Wang Xiao","year":"2022","unstructured":"Xiao Wang, Craig Macdonald, Nicola Tonellotto, and Iadh Ounis. 2022c. ColBERT-PRF: Semantic Pseudo-Relevance Feedback for Dense Passage and Document Retrieval. ACM Transactions on the Web (2022)."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of ICLR.","author":"Xiong Lee","year":"2021","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In Proceedings of ICLR."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462880"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.334"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"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\/3539618.3591916","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:38:07Z","timestamp":1750178287000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591916"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":40,"alternative-id":["10.1145\/3539618.3591916","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591916","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"}}]}}