{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:28:33Z","timestamp":1774308513490,"version":"3.50.1"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031887161","type":"print"},{"value":"9783031887178","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-88717-8_3","type":"book-chapter","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T12:07:33Z","timestamp":1743768453000},"page":"21-30","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["ColBERT-Serve: Efficient Multi-stage Memory-Mapped Scoring"],"prefix":"10.1007","author":[{"given":"Kaili","family":"Huang","sequence":"first","affiliation":[]},{"given":"Thejas","family":"Venkatesh","sequence":"additional","affiliation":[]},{"given":"Uma","family":"Dingankar","sequence":"additional","affiliation":[]},{"given":"Antonio","family":"Mallia","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Campos","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Jiao","sequence":"additional","affiliation":[]},{"given":"Christopher","family":"Potts","sequence":"additional","affiliation":[]},{"given":"Matei","family":"Zaharia","sequence":"additional","affiliation":[]},{"given":"Kwabena","family":"Boahen","sequence":"additional","affiliation":[]},{"given":"Omar","family":"Khattab","sequence":"additional","affiliation":[]},{"given":"Saarthak","family":"Sarup","sequence":"additional","affiliation":[]},{"given":"Keshav","family":"Santhanam","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,3]]},"reference":[{"key":"3_CR1","unstructured":"Bajaj, P., et\u00a0al.: MS MARCO: a human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268 (2016)"},{"key":"3_CR2","unstructured":"Basnet, S., Gou, J., Mallia, A., Suel, T.: DeeperImpact: optimizing sparse learned index structures. arXiv preprint arXiv:2405.17093 (2024)"},{"key":"3_CR3","unstructured":"Bergum, J.K.: Improving zero-shot ranking with Vespa hybrid search - part two (2023). https:\/\/blog.vespa.ai\/improving-zero-shot-ranking-with-vespa-part-two\/"},{"key":"3_CR4","unstructured":"Bernhardsson, E.: Spotify\/Annoy: approximate nearest neighbors in C++\/Python optimized for memory usage and loading\/saving to disk. https:\/\/github.com\/spotify\/annoy"},{"key":"3_CR5","unstructured":"Faysse, M., Sibille, H., Wu, T., Omrani, B., Viaud, G., Hudelot, C., Colombo, P.: ColPali: efficient document retrieval with vision language models (2024). https:\/\/arxiv.org\/abs\/2407.01449"},{"key":"3_CR6","doi-asserted-by":"publisher","unstructured":"Formal, T., Clinchant, S., D\u00e9jean, H., Lassance, C.: SPLATE: sparse late interaction retrieval. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2635\u20132640. SIGIR \u201924, Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3626772.3657968","DOI":"10.1145\/3626772.3657968"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Formal, T., Lassance, C., Piwowarski, B., Clinchant, S.: SPLADE v2: sparse lexical and expansion model for information retrieval. CoRR abs\/2109.10086 (2021). https:\/\/arxiv.org\/abs\/2109.10086","DOI":"10.1145\/3404835.3463098"},{"key":"3_CR8","doi-asserted-by":"publisher","unstructured":"Hofst\u00e4tter, S., Khattab, O., Althammer, S., Sertkan, M., Hanbury, A.: Introducing neural bag of whole-words with colberter: contextualized late interactions using enhanced reduction. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 737\u2013747. CIKM \u201922, Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3511808.3557367","DOI":"10.1145\/3511808.3557367"},{"issue":"3","key":"3_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":"3_CR10","doi-asserted-by":"publisher","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. SIGIR \u201920, Association for Computing Machinery, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3397271.3401075","DOI":"10.1145\/3397271.3401075"},{"key":"3_CR11","unstructured":"Kotek, J.: Jankotek\/mapdb: Mapdb provides concurrent maps, sets and queues backed by disk storage or off-heap-memory it is a fast and easy to use embedded java database engine. https:\/\/github.com\/jankotek\/mapdb\/"},{"key":"3_CR12","doi-asserted-by":"publisher","unstructured":"Kulkarni, H., MacAvaney, S., Goharian, N., Frieder, O.: Lexically-accelerated dense retrieval. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 152\u2013162. SIGIR \u201923, Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3539618.3591715","DOI":"10.1145\/3539618.3591715"},{"key":"3_CR13","doi-asserted-by":"publisher","unstructured":"Kwiatkowski, T., et al.: Natural Questions: a benchmark for question answering research. Transactions of the Association for Computational Linguistics 7, 453\u2013466 (2019). https:\/\/doi.org\/10.1162\/tacl_a_00276","DOI":"10.1162\/tacl_a_00276"},{"key":"3_CR14","doi-asserted-by":"publisher","unstructured":"Lassance, C., Clinchant, S.: An efficiency study for splade models. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2220\u20132226. SIGIR \u201922, Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3477495.3531833, https:\/\/doi.org\/10.1145\/3477495.3531833","DOI":"10.1145\/3477495.3531833"},{"key":"3_CR15","unstructured":"Lee, J., Dai, Z., Duddu, S.M.K., Lei, T., Naim, I., Chang, M.W., Zhao, V.: Rethinking the role of token retrieval in multi-vector retrieval. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"3_CR16","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. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1612"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Citadel: conditional token interaction via dynamic lexical routing for efficient and effective multi-vector retrieval. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 11891\u201311907 (2023)","DOI":"10.18653\/v1\/2023.acl-long.663"},{"key":"3_CR18","unstructured":"Lin, J., Ma, X.: A few brief notes on DeepImpact, COIL, and a conceptual framework for information retrieval techniques. arXiv preprint arXiv:2106.14807 (2021)"},{"key":"3_CR19","doi-asserted-by":"publisher","unstructured":"MacAvaney, S., Tonellotto, N.: A reproducibility study of plaid. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1411\u20131419. SIGIR \u201924, Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3626772.3657856, https:\/\/doi.org\/10.1145\/3626772.3657856","DOI":"10.1145\/3626772.3657856"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Mackenzie, J., Mallia, A., Moffat, A., Petri, M.: Accelerating learned sparse indexes via term impact decomposition. In: Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 2830\u20132842 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.205"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Mallia, A., Khattab, O., Suel, T., Tonellotto, N.: Learning passage impacts for inverted indexes. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1723\u20131727 (2021)","DOI":"10.1145\/3404835.3463030"},{"key":"3_CR22","unstructured":"Mallia, A., Siedlaczek, M., Mackenzie, J., Suel, T.: PISA: performant indexes and search for academia. In: Proceedings of the Open-Source IR Replicability Challenge co-located with 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, OSIRRC@SIGIR 2019, Paris, France, July 25, 2019, pp. 50\u201356 (2019). http:\/\/ceur-ws.org\/Vol-2409\/docker08.pdf"},{"key":"3_CR23","doi-asserted-by":"publisher","unstructured":"Mallia, A., Siedlaczek, M., Suel, T.: An experimental study of index compression and DAAT query processing methods. In: Azzopardi, L., Stein, B., Fuhr, N., Mayr, P., Hauff, C., Hiemstra, D. (eds.) ECIR 2019. LNCS, vol. 11437, pp. 353\u2013368. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-15712-8_23","DOI":"10.1007\/978-3-030-15712-8_23"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Mallia, A., Suel, T., Tonellotto, N.: Faster learned sparse retrieval with block-max pruning. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2411\u20132415 (2024)","DOI":"10.1145\/3626772.3657906"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Nardini, F.M., Rulli, C., Venturini, R.: Efficient multi-vector dense retrieval with bit vectors. In: European Conference on Information Retrieval, pp. 3\u201317. Springer (2024)","DOI":"10.1007\/978-3-031-56060-6_1"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Robertson, S., Walker, S., Jones, S., Hancock-Beaulieu, M.M., Gatford, M.: Okapi at TREC-3. In: Overview of the Third Text REtrieval Conference (TREC-3), pp. 109\u2013126. Gaithersburg, MD: NIST (1995). https:\/\/www.microsoft.com\/en-us\/research\/publication\/okapi-at-trec-3\/","DOI":"10.6028\/NIST.SP.500-225.routing-city"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Santhanam, K., Khattab, O., Potts, C., Zaharia, M.: Plaid: an efficient engine for late interaction retrieval. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 1747\u20131756 (2022)","DOI":"10.1145\/3511808.3557325"},{"key":"3_CR28","doi-asserted-by":"publisher","unstructured":"Santhanam, K., Khattab, O., Saad-Falcon, J., Potts, C., Zaharia, M.: ColBERTv2: effective and efficient retrieval via lightweight late interaction. In: Carpuat, M., de\u00a0Marneffe, M.C., eza\u00a0Ruiz, I.V. (eds.) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 3715\u20133734. Association for Computational Linguistics, Seattle, United States (2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.272, https:\/\/aclanthology.org\/2022.naacl-main.272","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"3_CR29","doi-asserted-by":"publisher","unstructured":"Santhanam, K., et al.: Moving beyond downstream task accuracy for information retrieval benchmarking. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Findings of the Association for Computational Linguistics: ACL 2023, pp. 11613\u201311628. Association for Computational Linguistics, Toronto, Canada (Jul 2023https:\/\/doi.org\/10.18653\/v1\/2023.findings-acl.738, https:\/\/aclanthology.org\/2023.findings-acl.738","DOI":"10.18653\/v1\/2023.findings-acl.738"},{"key":"3_CR30","doi-asserted-by":"publisher","unstructured":"Shrestha, S., Reddy, N., Li, Z.: ESPN: memory-efficient multi-vector information retrieval. In: Proceedings of the 2024 ACM SIGPLAN International Symposium on Memory Management, pp. 95\u2013107. ISMM 2024, Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3652024.3665515","DOI":"10.1145\/3652024.3665515"},{"key":"3_CR31","unstructured":"Thakur, N., Reimers, N., R\u00fcckl\u00e9, A., Srivastava, A., Gurevych, I.: BEIR: a heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663 (2021)"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Yu, P., Mallia, A., Petri, M.: Improved learned sparse retrieval with corpus-specific vocabularies. In: European Conference on Information Retrieval, pp. 181\u2013194. Springer (2024)","DOI":"10.1007\/978-3-031-56063-7_12"},{"key":"3_CR33","unstructured":"Zhuang, S., Zuccon, G.: Fast passage re-ranking with contextualized exact term matching and efficient passage expansion. arXiv preprint arXiv:2108.08513 (2021)"}],"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\/978-3-031-88717-8_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T09:22:47Z","timestamp":1746696167000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-88717-8_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031887161","9783031887178"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-88717-8_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"3 April 2025","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":"Lucca","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"47","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2025.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}