{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:17:25Z","timestamp":1759331845946,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031333798"},{"type":"electronic","value":"9783031333804"}],"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\/978-3-031-33380-4_10","type":"book-chapter","created":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T08:05:58Z","timestamp":1685088358000},"page":"125-137","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Isotropic Representation Can Improve Dense Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8148-8735","authenticated-orcid":false,"given":"Euna","family":"Jung","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9214-3073","authenticated-orcid":false,"given":"Jungwon","family":"Park","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1992-0731","authenticated-orcid":false,"given":"Jaekeol","family":"Choi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0287-5276","authenticated-orcid":false,"given":"Sungyoon","family":"Kim","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2590-8774","authenticated-orcid":false,"given":"Wonjong","family":"Rhee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,27]]},"reference":[{"key":"10_CR1","unstructured":"Callan, J., Hoy, M., Yoo, C., Zhao, L.: Clueweb09 data set (2009)"},{"key":"10_CR2","unstructured":"Dinh, L., Krueger, D., Bengio, Y.: Nice: non-linear independent components estimation. arXiv preprint arXiv:1410.8516 (2014)"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Ethayarajh, K.: How contextual are contextualized word representations? Comparing the geometry of BERT, ELMO, and GPT-2 embeddings. arXiv preprint arXiv:1909.00512 (2019)","DOI":"10.18653\/v1\/D19-1006"},{"issue":"397","key":"10_CR4","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1080\/01621459.1987.10478427","volume":"82","author":"JH Friedman","year":"1987","unstructured":"Friedman, J.H.: Exploratory projection pursuit. J. Am. Stat. Assoc. 82(397), 249\u2013266 (1987)","journal-title":"J. Am. Stat. Assoc."},{"key":"10_CR5","unstructured":"Gao, J., He, D., Tan, X., Qin, T., Wang, L., Liu, T.Y.: Representation degeneration problem in training natural language generation models. arXiv preprint arXiv:1907.12009 (2019)"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Gao, L., Dai, Z., Callan, J.: Coil: revisit exact lexical match in information retrieval with contextualized inverted list. arXiv preprint arXiv:2104.07186 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.241"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Goren, G., Kurland, O., Tennenholtz, M., Raiber, F.: Ranking robustness under adversarial document manipulations. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 395\u2013404 (2018)","DOI":"10.1145\/3209978.3210012"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Huston, S., Croft, W.B.: Parameters learned in the comparison of retrieval models using term dependencies. University of Massachusetts, IR (2014)","DOI":"10.1145\/2661829.2661894"},{"issue":"3","key":"10_CR9","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","volume":"7","author":"J Johnson","year":"2019","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. IEEE Trans. Big Data 7(3), 535\u2013547 (2019)","journal-title":"IEEE Trans. Big Data"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Jung, E., Choi, J., Rhee, W.: Semi-Siamese Bi-encoder neural ranking model using lightweight fine-tuning. In: Proceedings of the ACM Web Conference 2022, pp. 502\u2013511 (2022)","DOI":"10.1145\/3485447.3511978"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Khattab, O., Zaharia, M.: 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, pp. 39\u201348 (2020)","DOI":"10.1145\/3397271.3401075"},{"key":"10_CR13","unstructured":"Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1$$\\times $$1 convolutions. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"issue":"11","key":"10_CR14","doi-asserted-by":"publisher","first-page":"3964","DOI":"10.1109\/TPAMI.2020.2992934","volume":"43","author":"I Kobyzev","year":"2020","unstructured":"Kobyzev, I., Prince, S.J., Brubaker, M.A.: Normalizing flows: an introduction and review of current methods. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 3964\u20133979 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Kovaleva, O., Kulshreshtha, S., Rogers, A., Rumshisky, A.: BERT busters: outlier dimensions that disrupt transformers. arXiv preprint arXiv:2105.06990 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.300"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Li, B., Zhou, H., He, J., Wang, M., Yang, Y., Li, L.: On the sentence embeddings from pre-trained language models. arXiv preprint arXiv:2011.05864 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.733"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Luo, Z., Kulmizev, A., Mao, X.: Positional artefacts propagate through masked language model embeddings. arXiv preprint arXiv:2011.04393 (2020)","DOI":"10.18653\/v1\/2021.acl-long.413"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"MacAvaney, S., Yates, A., Cohan, A., Goharian, N.: CEDR: contextualized embeddings for document ranking. In: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1101\u20131104 (2019)","DOI":"10.1145\/3331184.3331317"},{"key":"10_CR19","unstructured":"Mu, J., Bhat, S., Viswanath, P.: All-but-the-top: simple and effective postprocessing for word representations. arXiv preprint arXiv:1702.01417 (2017)"},{"key":"10_CR20","unstructured":"Mussmann, S., Ermon, S.: Learning and inference via maximum inner product search. In: International Conference on Machine Learning, pp. 2587\u20132596. PMLR (2016)"},{"key":"10_CR21","unstructured":"Nguyen, T., et al.: MS MARCO: a human generated machine reading comprehension dataset. In: CoCo@ NIPS (2016)"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Qu, Y., et al.: RocketQA: an optimized training approach to dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2010.08191 (2020)","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"10_CR23","unstructured":"Su, J., Cao, J., Liu, W., Ou, Y.: Whitening sentence representations for better semantics and faster retrieval. arXiv preprint arXiv:2103.15316 (2021)"},{"issue":"2","key":"10_CR24","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1002\/cpa.21423","volume":"66","author":"EG Tabak","year":"2013","unstructured":"Tabak, E.G., Turner, C.V.: A family of nonparametric density estimation algorithms. Commun. Pure Appl. Math. 66(2), 145\u2013164 (2013)","journal-title":"Commun. Pure Appl. Math."},{"issue":"1","key":"10_CR25","doi-asserted-by":"publisher","first-page":"217","DOI":"10.4310\/CMS.2010.v8.n1.a11","volume":"8","author":"EG Tabak","year":"2010","unstructured":"Tabak, E.G., Vanden-Eijnden, E.: Density estimation by dual ascent of the log-likelihood. Commun. Math. Sci. 8(1), 217\u2013233 (2010)","journal-title":"Commun. Math. Sci."},{"key":"10_CR26","unstructured":"Thakur, N., Reimers, N., Lin, J.: Domain adaptation for memory-efficient dense retrieval. arXiv preprint arXiv:2205.11498 (2022)"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Timkey, W., van Schijndel, M.: All bark and no bite: rogue dimensions in transformer language models obscure representational quality. arXiv preprint arXiv:2109.04404 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.372"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Voorhees, E.M., et al.: Overview of TREC 2004. In: TREC (2004)","DOI":"10.6028\/NIST.SP.500-261.overview-overview"},{"key":"10_CR29","unstructured":"Wang, L., Huang, J., Huang, K., Hu, Z., Wang, G., Gu, Q.: Improving neural language generation with spectrum control. In: International Conference on Learning Representations (2019)"},{"key":"10_CR30","unstructured":"Wu, C., Zhang, R., Guo, J., Fan, Y., Cheng, X.: Are neural ranking models robust? arXiv preprint arXiv:2108.05018 (2021)"},{"key":"10_CR31","unstructured":"Xiong, L., et al.: Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808 (2020)"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Yu, S., Song, J., Kim, H., Lee, S., Ryu, W.J., Yoon, S.: Rare tokens degenerate all tokens: improving neural text generation via adaptive gradient gating for rare token embeddings. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, vol. 1 (Long Papers), pp. 29\u201345 (2022)","DOI":"10.18653\/v1\/2022.acl-long.3"},{"key":"10_CR33","unstructured":"Zhan, J., Mao, J., Liu, Y., Zhang, M., Ma, S.: RepBERT: contextualized text embeddings for first-stage retrieval. arXiv preprint arXiv:2006.15498 (2020)"},{"key":"10_CR34","unstructured":"Zhang, T., Wu, F., Katiyar, A., Weinberger, K.Q., Artzi, Y.: Revisiting few-sample BERT fine-tuning. arXiv preprint arXiv:2006.05987 (2020)"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-33380-4_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T04:34:59Z","timestamp":1729485299000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-33380-4_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031333798","9783031333804"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-33380-4_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"27 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Osaka","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"25 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2023.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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"813","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":"143","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":"18% - 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":"3.5","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":"10","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)"}}]}}