{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:18:59Z","timestamp":1784179139158,"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_12","type":"book-chapter","created":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T08:44:01Z","timestamp":1711097041000},"page":"181-194","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Improved Learned Sparse Retrieval with\u00a0Corpus-Specific Vocabularies"],"prefix":"10.1007","author":[{"given":"Puxuan","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"Mallia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Petri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,23]]},"reference":[{"issue":"4","key":"12_CR1","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/s10791-022-09411-0","volume":"25","author":"N Arabzadeh","year":"2022","unstructured":"Arabzadeh, N., Vtyurina, A., Yan, X., Clarke, C.: Shallow pooling for sparse labels. Inf. Retrieval 25(4), 365\u2013385 (2022)","journal-title":"Inf. Retrieval"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Aslam, J., Montague, M.: Models for metasearch. In: Proceedings of ACM International Conference on Information and Knowledge Management (CIKM), pp. 276\u2013284 (2001)","DOI":"10.1145\/383952.384007"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Craswell, N., Mitra, B., Yilmaz, E., Campos, D.: Overview of the TREC 2020 deep learning track. arXiv:2102.07662 (2021)","DOI":"10.6028\/NIST.SP.1266.deep-overview"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Craswell, N., Mitra, B., Yilmaz, E., Campos, D., Voorhees, E.M.: Overview of the TREC 2019 deep learning track. arXiv:2003.07820 (2020)","DOI":"10.6028\/NIST.SP.1266.deep-overview"},{"key":"12_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding, pp. 4171\u20134186 (2019)"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Dhulipala, L., Kabiljo, I., Karrer, B., Ottaviano, G., Pupyrev, S., Shalita, A.: Compressing graphs and indexes with recursive graph bisection. In: Proceedings of Conference on Knowledge Discovery and Data Mining (KDD), pp. 1535\u20131544 (2016)","DOI":"10.1145\/2939672.2939862"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Ding, S., Suel, T.: Faster top-$$k$$ document retrieval using block-max indexes. In: Proceedings of ACM International Conference on Research and Development in Information Retrieval (SIGIR), pp. 993\u20131002 (2011)","DOI":"10.1145\/2009916.2010048"},{"key":"12_CR8","unstructured":"Feng, Z., et al.: Pretraining without wordpieces: learning over a vocabulary of millions of words (2022)"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Formal, T., Lassance, C., Piwowarski, B., Clinchant, S.: SPLADE v2: sparse lexical and expansion model for information retrieval. arXiv:2109.10086 (2021)","DOI":"10.1145\/3404835.3463098"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Formal, T., Piwowarski, B., Clinchant, S.: SPLADE: sparse lexical and expansion model for first stage ranking. In: Proceedings of ACM International Conference on Research and Development in Information Retrieval (SIGIR), pp. 2288\u20132292 (2021)","DOI":"10.1145\/3404835.3463098"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Gao, L., Callan, J.: Unsupervised corpus aware language model pre-training for dense passage retrieval, pp. 2843\u20132853 (2022)","DOI":"10.18653\/v1\/2022.acl-long.203"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Gao, L., Dai, Z., Callan, J.: COIL: revisit exact lexical match in information retrieval with contextualized inverted list, pp. 3030\u20133042 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.241"},{"key":"12_CR13","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv:1503.02531 (2015)"},{"issue":"1","key":"12_CR14","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1214\/aoms\/1177729694","volume":"22","author":"S Kullback","year":"1951","unstructured":"Kullback, S., Leibler, R.: On information and sufficiency. Ann. Math. Stat. 22(1), 79\u201386 (1951)","journal-title":"Ann. Math. Stat."},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Lassance, C., Clinchant, S.: An efficiency study for SPLADE models. In: Proceedings of ACM International Conference on Research and Development in Information Retrieval (SIGIR), pp. 2220\u20132226 (2022)","DOI":"10.1145\/3477495.3531833"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Lassance, C., D\u00e9jean, H., Clinchant, S.: An experimental study on pretraining transformers from scratch for IR. arXiv:2301.10444 (2023)","DOI":"10.1007\/978-3-031-28244-7_32"},{"key":"12_CR17","unstructured":"Lin, J., Ma, X.: A few brief notes on DeepImpact, COIL, and a conceptual framework for information retrieval techniques. arXiv:2106.14807 (2021)"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Mackenzie, J., Mallia, A., Moffat, A., Petri, M.: Accelerating learned sparse indexes via term impact decomposition, pp. 18\u201327 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.205"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Mackenzie, J., Mallia, A., Petri, M., Culpepper, J.S., Suel, T.: Compressing inverted indexes with recursive graph bisection: a reproducibility study. In: Proceedings of European Conference on Information Retrieval (ECIR), pp. 339\u2013352 (2019)","DOI":"10.1007\/978-3-030-15712-8_22"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Mackenzie, J., Petri, M., Moffat, A.: Faster index reordering with bipartite graph partitioning. In: Proceedings of ACM International Conference on Research and Development in Information Retrieval (SIGIR), pp. 1910\u20131914 (2021)","DOI":"10.1145\/3404835.3462991"},{"key":"12_CR21","unstructured":"Mackenzie, J., Petri, M., Moffat, A.: A sensitivity analysis of the MSMARCO passage collection. arXiv:2112.03396 (2021)"},{"key":"12_CR22","unstructured":"Mackenzie, J., Trotman, A., Lin, J.: Wacky weights in learned sparse representations and the revenge of score-at-a-time query evaluation. arXiv:2110.11540 (2021)"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Mallia, A., Khattab, O., Tonellotto, N., Suel, T.: Learning passage impacts for inverted indexes. In: Proceedings of ACM International Conference on Research and Development in Information Retrieval (SIGIR), pp. 1723\u20131727 (2021)","DOI":"10.1145\/3404835.3463030"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Mallia, A., Mackenzie, J., Suel, T., Tonellotto, N.: Faster learned sparse retrieval with guided traversal. In: Proceedings of ACM International Conference on Research and Development in Information Retrieval (SIGIR), pp. 1901\u20131905 (2022)","DOI":"10.1145\/3477495.3531774"},{"key":"12_CR25","unstructured":"Mallia, A., Siedlaczek, M., Mackenzie, J., Suel, T.: PISA: performant indexes and search for academia. In: Proceedings of OSIRRC at SIGIR 2019, pp. 50\u201356 (2019)"},{"key":"12_CR26","unstructured":"Nogueira, R., Cho, K.: Passage re-ranking with bert. arXiv preprint arXiv:1901.04085 (2019)"},{"key":"12_CR27","unstructured":"Nogueira, R., Lin, J.: From doc2query to docTTTTTquery (2019)"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Ottaviano, G., Venturini, R.: Partitioned Elias-Fano indexes. In: Proceedings of ACM International Conference on Research and Development in Information Retrieval (SIGIR), pp. 273\u2013282 (2014)","DOI":"10.1145\/2600428.2609615"},{"key":"12_CR29","unstructured":"Paria, B., Yeh, C., Yen, I., Xu, N., Ravikumar, P., P\u00f3czos, B.: Minimizing flops to learn efficient sparse representations. arXiv:2004.05665 (2020)"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Pibiri, G.E., Venturini, R.: Techniques for inverted index compression. ACM Comput. Surv. 53(6), 125.1\u2013125.36 (2021)","DOI":"10.1145\/3415148"},{"key":"12_CR31","unstructured":"Reimers, N.: MS MARCO Passages Hard Negatives. In: HuggingFace, pp. 1747\u20131756 (2021). https:\/\/huggingface.co\/datasets\/sentence-transformers\/msmarco-hard-negatives"},{"key":"12_CR32","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1561\/1500000019","volume":"3","author":"SE Robertson","year":"2009","unstructured":"Robertson, S.E., Zaragoza, H.: The probabilistic relevance framework: BM25 and beyond. Found. Trends Inf. Retrieval 3, 333\u2013389 (2009)","journal-title":"Found. Trends Inf. Retrieval"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Santhanam, K., Khattab, O., Potts, C., Zaharia, M.: PLAID: an efficient engine for late interaction retrieval. In: Proceedings of ACM International Conference on Information and Knowledge Management (CIKM), pp. 1747\u20131756. ACM (2022)","DOI":"10.1145\/3511808.3557325"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Santhanam, K., Khattab, O., Saad-Falcon, J., Potts, C., Zaharia, M.: Colbertv2: effective and efficient retrieval via lightweight late interaction. In: NAACL, pp. 3715\u20133734 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units (2016)","DOI":"10.18653\/v1\/P16-1162"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Siedlaczek, M., Mallia, A., Suel, T.: Using conjunctions for faster disjunctive top-k queries. In: Proceedings of Conference on Web Search and Data Mining (WSDM), pp. 917\u2013927 (2022)","DOI":"10.1145\/3488560.3498489"},{"issue":"6","key":"12_CR37","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1016\/0306-4573(95)00020-H","volume":"31","author":"HR Turtle","year":"1995","unstructured":"Turtle, H.R., Flood, J.: Query evaluation: strategies and optimizations. Inf. Process. Manag. 31(6), 831\u2013850 (1995)","journal-title":"Inf. Process. Manag."},{"key":"12_CR38","unstructured":"Wu, Y., et al.: Google\u2019s neural machine translation system: bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: Dict-BERT: enhancing language model pre-training with dictionary (2022)","DOI":"10.18653\/v1\/2022.findings-acl.150"},{"issue":"2","key":"12_CR40","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1145\/2422256.2422277","volume":"46","author":"L Zhao","year":"2012","unstructured":"Zhao, L.: Modeling and solving term mismatch for full-text retrieval. SIGIR Forum 46(2), 117\u2013118 (2012)","journal-title":"SIGIR Forum"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Zhuang, S., Zuccon, G.: TILDE: term independent likelihood moDEl for passage re-ranking. In: Proceedings of ACM International Conference on Research and Development in Information Retrieval (SIGIR), pp. 1483\u20131492 (2021)","DOI":"10.1145\/3404835.3462922"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Zobel, J., Moffat, A.: Inverted files for text search engines. ACM Comput. Surv. 38(2), 6:1\u20136:56 (2006)","DOI":"10.1145\/1132956.1132959"}],"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_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T21:30:49Z","timestamp":1731619849000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-56063-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031560620","9783031560637"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-56063-7_12","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)"}}]}}