{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:48:52Z","timestamp":1743122932737,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031278174"},{"type":"electronic","value":"9783031278181"}],"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\/978-3-031-27818-1_25","type":"book-chapter","created":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T10:20:17Z","timestamp":1680171617000},"page":"301-312","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HSS: A Hierarchical Semantic Similarity Hard Negative Sampling Method for\u00a0Dense Retrievers"],"prefix":"10.1007","author":[{"given":"Xinjia","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shun","family":"Gai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghao","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,31]]},"reference":[{"key":"25_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1007\/978-3-319-24027-5_20","volume-title":"Experimental IR Meets Multilinguality, Multimodality, and Interaction","author":"P Baudi\u0161","year":"2015","unstructured":"Baudi\u0161, P., \u0160ediv\u00fd, J.: Modeling of the question answering task in the YodaQA system. In: Mothe, J., et al. (eds.) CLEF 2015. LNCS, vol. 9283, pp. 222\u2013228. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24027-5_20"},{"key":"25_CR2","unstructured":"Berant, J., Chou, A., Frostig, R., Liang, P.: Semantic parsing on freebase from question-answer pairs. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1533\u20131544 (2013)"},{"key":"25_CR3","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3(Jan), 993\u20131022 (2003)"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Dolan, W., Quirk, C., Brockett, C., Dolan, B.: Unsupervised construction of large paraphrase corpora: exploiting massively parallel news sources (2004)","DOI":"10.3115\/1220355.1220406"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Gillick, D., et al.: Learning dense representations for entity retrieval. In: Proceedings of the 23rd Conference on Computational Natural Language Learning, pp. 528\u2013537 (2019)","DOI":"10.18653\/v1\/K19-1049"},{"key":"25_CR6","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"},{"issue":"3","key":"25_CR7","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":"25_CR8","doi-asserted-by":"crossref","unstructured":"Joshi, M., Choi, E., Weld, D.S., Zettlemoyer, L.: Triviaqa: a large scale distantly supervised challenge dataset for reading comprehension. In: Proceedings of the 55th Meeting of the Association for Computational Linguistics, pp. 1601\u20131611 (2017)","DOI":"10.18653\/v1\/P17-1147"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pp. 6769\u20136781 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Kulis, B., et al.: Metric learning: a survey. Found. Trends\u00ae Mach. Learn. 5(4), 287\u2013364 (2013)","DOI":"10.1561\/2200000019"},{"key":"25_CR11","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1162\/tacl_a_00276","volume":"7","author":"T Kwiatkowski","year":"2019","unstructured":"Kwiatkowski, T., et al.: Natural questions: a benchmark for question answering research. Trans. Assoc. Comput. Linguist. 7, 453\u2013466 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Lee, K., Chang, M.W., Toutanova, K.: Latent retrieval for weakly supervised open domain question answering. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 6086\u20136096 (2019)","DOI":"10.18653\/v1\/P19-1612"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Li, H., Xu, J., et al.: Semantic matching in search. Found. Trends\u00ae Inf. Retrieval 7(5), 343\u2013469 (2014)","DOI":"10.1561\/1500000035"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Y., Hashimoto, K., Zhou, Y., Yavuz, S., Xiong, C., Philip, S.Y.: Dense hierarchical retrieval for open-domain question answering. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 188\u2013200 (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.19"},{"key":"25_CR15","unstructured":"Marelli, M., Menini, S., Baroni, M., Bentivogli, L., Bernardi, R., Zamparelli, R.: A sick cure for the evaluation of compositional distributional semantic models. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014), pp. 216\u2013223 (2014)"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Ren, R., et al.: A thorough examination on zero-shot dense retrieval. arXiv preprint arXiv:2204.12755 (2022)","DOI":"10.18653\/v1\/2023.findings-emnlp.1057"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Sciavolino, C., Zhong, Z., Lee, J., Chen, D.: Simple entity-centric questions challenge dense retrievers. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 6138\u20136148 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.496"},{"key":"25_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1007\/978-3-030-58568-6_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Xuan","year":"2020","unstructured":"Xuan, H., Stylianou, A., Liu, X., Pless, R.: Hard negative examples are hard, but useful. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 126\u2013142. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_8"},{"key":"25_CR19","unstructured":"Yih, W.T., Toutanova, K., Platt, J.C., Meek, C.: Learning discriminative projections for text similarity measures. In: Proceedings of the 15th Conference on Computational Natural Language Learning, pp. 247\u2013256 (2011)"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Zhan, J., Mao, J., Liu, Y., Guo, J., Zhang, M., Ma, S.: Optimizing dense retrieval model training with hard negatives. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1503\u20131512 (2021)","DOI":"10.1145\/3404835.3462880"},{"key":"25_CR21","unstructured":"Zhang, D., et al.: Supporting clustering with contrastive learning. In: NAACL-HLT (2021)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27818-1_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T10:05:41Z","timestamp":1729159541000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27818-1_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031278174","9783031278181"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27818-1_25","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":"31 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bergen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","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":"9 January 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 January 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2023","order":10,"name":"conference_id","label":"Conference ID","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":"Conftool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"267","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":"86","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":"32% - 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)"}}]}}