{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:27:31Z","timestamp":1783736851555,"version":"3.55.0"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031560620","type":"print"},{"value":"9783031560637","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-56063-7_16","type":"book-chapter","created":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T08:44:01Z","timestamp":1711097041000},"page":"243-258","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["InDi: Informative and\u00a0Diverse Sampling for\u00a0Dense Retrieval"],"prefix":"10.1007","author":[{"given":"Nachshon","family":"Cohen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hedda","family":"Cohen-Indelman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaron","family":"Fairstein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guy","family":"Kushilevitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,23]]},"reference":[{"key":"16_CR1","unstructured":"Ash, J.T., Zhang, C., Krishnamurthy, A., Langford, J., Agarwal, A.: Deep batch active learning by diverse, uncertain gradient lower bounds. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020. OpenReview.net (2020)"},{"key":"16_CR2","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2\u20137, 2019, Volume 1 (Long and Short Papers). pp. 4171\u20134186. Association for Computational Linguistics (2019)"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Formal, T., Lassance, C., Piwowarski, B., Clinchant, S.: Splade v2: Sparse lexical and expansion model for information retrieval. arXiv preprint arXiv:2109.10086 (2021)","DOI":"10.1145\/3404835.3463098"},{"issue":"2","key":"16_CR4","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/s10115-012-0507-8","volume":"35","author":"Y Fu","year":"2013","unstructured":"Fu, Y., Zhu, X., Li, B.: A survey on instance selection for active learning. Knowl. Inf. Syst. 35(2), 249\u2013283 (2013)","journal-title":"Knowl. Inf. Syst."},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Gao, L., Callan, J.: Condenser: a pre-training architecture for dense retrieval. In: Moens, M., Huang, X., Specia, L., Yih, S.W. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event \/ Punta Cana, Dominican Republic, 7\u201311 November, 2021. pp. 981\u2013993. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.75"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Gao, L., Callan, J.: Condenser: a pre-training architecture for dense retrieval. arXiv preprint arXiv:2104.08253 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.75"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Gao, L., Callan, J.: Unsupervised corpus aware language model pre-training for dense passage retrieval. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). pp. 2843\u20132853. Association for Computational Linguistics, Dublin, Ireland (May 2022)","DOI":"10.18653\/v1\/2022.acl-long.203"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Gao, L., Ma, X., Lin, J., Callan, J.: Tevatron: An efficient and flexible toolkit for dense retrieval. CoRR abs\/2203.05765 (2022)","DOI":"10.1145\/3539618.3591805"},{"key":"16_CR9","unstructured":"Gissin, D., Shalev-Shwartz, S.: Discriminative active learning. CoRR abs\/1907.06347 (2019)"},{"key":"16_CR10","unstructured":"Guo, R., Sun, P., Lindgren, E., Geng, Q., Simcha, D., Chern, F., Kumar, S.: Accelerating large-scale inference with anisotropic vector quantization. In: International Conference on Machine Learning (2020)"},{"key":"16_CR11","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.: Retrieval augmented language model pre-training. In: International Conference on Machine Learning. pp. 3929\u20133938. PMLR (2020)"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Hofst\u00e4tter, S., Lin, S.C., Yang, J.H., Lin, J., Hanbury, A.: 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. pp. 113\u2013122 (2021)","DOI":"10.1145\/3404835.3462891"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Hofst\u00e4tter, S., Lin, S., Yang, J., Lin, J., Hanbury, A.: Efficiently teaching an effective dense retriever with balanced topic aware sampling. In: Diaz, F., Shah, C., Suel, T., Castells, P., Jones, R., Sakai, T. (eds.) SIGIR \u201921: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11\u201315, 2021. pp. 113\u2013122. ACM (2021)","DOI":"10.1145\/3404835.3462891"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Huang, P.S., He, X., Gao, J., Deng, L., Acero, A., Heck, L.: Learning deep structured semantic models for web search using clickthrough data. In: Proceedings of the 22nd ACM international conference on Information & Knowledge Management. pp. 2333\u20132338 (2013)","DOI":"10.1145\/2505515.2505665"},{"key":"16_CR15","unstructured":"Huang, S.J., Jin, R., Zhou, Z.H.: Active learning by querying informative and representative examples. Advances in neural information processing systems 23 (2010)"},{"issue":"3","key":"16_CR16","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 Transactions on Big Data 7(3), 535\u2013547 (2019)","journal-title":"IEEE Transactions on Big Data"},{"key":"16_CR17","unstructured":"Jones, K.S.: A statistical interpretation of term specificity and its application in retrieval. Journal of documentation (1972)"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., Oguz, B., Min, S., Lewis, P.S.H., Wu, L., Edunov, S., Chen, D., Yih, W.: Dense passage retrieval for open-domain question answering. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16\u201320, 2020. pp. 6769\u20136781. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"16_CR19","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":"16_CR20","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1162\/tacl_a_00276","volume":"7","author":"T Kwiatkowski","year":"2019","unstructured":"Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., Toutanova, K., Jones, L., Kelcey, M., Chang, M.W., Dai, A.M., Uszkoreit, J., Le, Q., Petrov, S.: Natural questions: A benchmark for question answering research. Transactions of the Association for Computational Linguistics 7, 452\u2013466 (2019)","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"16_CR21","first-page":"452","volume":"7","author":"T Kwiatkowski","year":"2019","unstructured":"Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A.P., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., Toutanova, K., Jones, L., Kelcey, M., Chang, M., Dai, A.M., Uszkoreit, J., Le, Q., Petrov, S.: Natural questions a benchmark for question answering research. Trans. Assoc. Comput. Linguistics 7, 452\u2013466 (2019)","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Lee, K., Ippolito, D., Nystrom, A., Zhang, C., Eck, D., Callison-Burch, C., Carlini, N.: Deduplicating training data makes language models better. arXiv preprint arXiv:2107.06499 (2021)","DOI":"10.18653\/v1\/2022.acl-long.577"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Lewis, D.D.: A sequential algorithm for training text classifiers: Corrigendum and additional data. In: Acm Sigir Forum. vol. 29, pp. 13\u201319. ACM New York, NY, USA (1995)","DOI":"10.1145\/219587.219592"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Lin, Z., Gong, Y., Liu, X., Zhang, H., Lin, C., Dong, A., Jiao, J., Lu, J., Jiang, D., Majumder, R., et al.: Prod: Progressive distillation for dense retrieval. arXiv preprint arXiv:2209.13335 (2022)","DOI":"10.1145\/3543507.3583421"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Lu, J., \u00c1brego, G.H., Ma, J., Ni, J., Yang, Y.: Multi-stage training with improved negative contrast for neural passage retrieval. In: Moens, M., Huang, X., Specia, L., Yih, S.W. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event \/ Punta Cana, Dominican Republic, 7\u201311 November, 2021. pp. 6091\u20136103. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.492"},{"key":"16_CR26","unstructured":"Lu, Y., Liu, Y., Liu, J., Shi, Y., Huang, Z., Sun, S.F.Y., Tian, H., Wu, H., Wang, S., Yin, D., et al.: Ernie-search: Bridging cross-encoder with dual-encoder via self on-the-fly distillation for dense passage retrieval. arXiv preprint arXiv:2205.09153 (2022)"},{"key":"16_CR27","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1162\/tacl_a_00369","volume":"9","author":"Y Luan","year":"2021","unstructured":"Luan, Y., Eisenstein, J., Toutanova, K., Collins, M.: Sparse, dense, and attentional representations for text retrieval. Transactions of the Association for Computational Linguistics 9, 329\u2013345 (2021)","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Mackenzie, J., Dai, Z., Gallagher, L., Callan, J.: Efficiency implications of term weighting for passage retrieval. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 1821\u20131824 (2020)","DOI":"10.1145\/3397271.3401263"},{"key":"16_CR29","unstructured":"Nguyen, T., Rosenberg, M., Song, X., Gao, J., Tiwary, S., Majumder, R., Deng, L.: MS MARCO: A human generated machine reading comprehension dataset. In: Besold, T.R., Bordes, A., d\u2019Avila Garcez, A.S., Wayne, G. (eds.) Proceedings of the Workshop on Cognitive Computation: Integrating neural and symbolic approaches 2016 co-located with the 30th Annual Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain, December 9, 2016. CEUR Workshop Proceedings, vol. 1773. CEUR-WS.org (2016)"},{"key":"16_CR30","unstructured":"Nguyen, T., Rosenberg, M., Song, X., Gao, J., Tiwary, S., Majumder, R., Deng, L.: MS MARCO: A human generated machine reading comprehension dataset. In: Besold, T.R., Bordes, A., d\u2019Avila Garcez, A.S., Wayne, G. (eds.) Proceedings of the Workshop on Cognitive Computation: Integrating neural and symbolic approaches 2016 co-located with the 30th Annual Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain, December 9, 2016. CEUR Workshop Proceedings, vol. 1773. CEUR-WS.org (2016)"},{"key":"16_CR31","unstructured":"Nogueira, R., Lin, J., Epistemic, A.: From doc2query to doctttttquery. Online preprint 6 (2019)"},{"key":"16_CR32","unstructured":"Nogueira, R., Yang, W., Lin, J., Cho, K.: Document expansion by query prediction. arXiv preprint arXiv:1904.08375 (2019)"},{"issue":"3","key":"16_CR33","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1002\/j.2168-9830.2004.tb00809.x","volume":"93","author":"M Prince","year":"2004","unstructured":"Prince, M.: Does active learning work? a review of the research. J. Eng. Educ. 93(3), 223\u2013231 (2004)","journal-title":"J. Eng. Educ."},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Qu, Y., Ding, Y., Liu, J., Liu, K., Ren, R., Zhao, W.X., Dong, D., Wu, H., Wang, H.: Rocketqa: An optimized training approach to dense passage retrieval for open-domain question answering. In: Toutanova, K., Rumshisky, A., Zettlemoyer, L., Hakkani-T\u00fcr, D., Beltagy, I., Bethard, S., Cotterell, R., Chakraborty, T., Zhou, Y. (eds.) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, June 6\u201311, 2021. pp. 5835\u20135847. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"16_CR35","first-page":"109","volume":"109","author":"SE Robertson","year":"1995","unstructured":"Robertson, S.E., Walker, S., Jones, S., Hancock-Beaulieu, M.M., Gatford, M., et al.: Okapi at trec-3. Nist Special Publication Sp 109, 109 (1995)","journal-title":"Nist Special Publication Sp"},{"issue":"5","key":"16_CR36","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","volume":"24","author":"G Salton","year":"1988","unstructured":"Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Information processing & management 24(5), 513\u2013523 (1988)","journal-title":"Information processing & management"},{"key":"16_CR37","unstructured":"Wang, T., Isola, P.: Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13\u201318 July 2020, Virtual Event. Proceedings of Machine Learning Research, vol. 119, pp. 9929\u20139939. PMLR (2020)"},{"key":"16_CR38","unstructured":"Xiong, L., Xiong, C., Li, Y., Tang, K., Liu, J., Bennett, P.N., Ahmed, J., Overwijk, A.: Approximate nearest neighbor negative contrastive learning for dense text retrieval. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021. OpenReview.net (2021)"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Yuan, M., Lin, H., Boyd-Graber, J.L.: Cold-start active learning through self-supervised language modeling. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16\u201320, 2020. pp. 7935\u20137948. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.637"},{"key":"16_CR40","unstructured":"Zhao, W.X., Liu, J., Ren, R., Wen, J.R.: Dense text retrieval based on pretrained language models: A survey. arXiv preprint arXiv:2211.14876 (2022)"},{"key":"16_CR41","unstructured":"Zhao, W.X., Liu, J., Ren, R., Wen, J.R.: Dense text retrieval based on pretrained language models: A survey. arXiv preprint arXiv:2211.14876 (2022)"},{"key":"16_CR42","unstructured":"Zhdanov, F.: Diverse mini-batch active learning. arXiv preprint arXiv:1901.05954 (2019)"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-56063-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T08:50:00Z","timestamp":1711097400000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-56063-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031560620","9783031560637"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-56063-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"23 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 March 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 March 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ecir2024.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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"578","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":"110","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":"69","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":"19% - 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","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31 (Tracks: Workshop, Tutorial, Industry, Doctoral Consortium)","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}