{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:41:27Z","timestamp":1783737687178,"version":"3.55.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031887079","type":"print"},{"value":"9783031887086","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\/978-3-031-88708-6_7","type":"book-chapter","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T11:51:44Z","timestamp":1743767504000},"page":"101-115","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Token Pruning Optimization for\u00a0Efficient Multi-vector Dense Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8581-6733","authenticated-orcid":false,"given":"Shanxiu","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3986-6311","authenticated-orcid":false,"given":"Mutasem","family":"Al-Darabsah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2283-7672","authenticated-orcid":false,"given":"Suraj","family":"Nair","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5284-477X","authenticated-orcid":false,"given":"Jonathan","family":"May","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5682-8234","authenticated-orcid":false,"given":"Tarun","family":"Agarwal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1902-3387","authenticated-orcid":false,"given":"Tao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5724-9478","authenticated-orcid":false,"given":"Choon Hui","family":"Teo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,3]]},"reference":[{"key":"7_CR1","doi-asserted-by":"publisher","unstructured":"Acquavia, A., Macdonald, C., Tonellotto, N.: Static pruning for multi-representation dense retrieval. In: Proceedings of the ACM Symposium on Document Engineering 2023. DocEng \u201923, Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3573128.3604896","DOI":"10.1145\/3573128.3604896"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Bird, S., Loper, E.: NLTK: the natural language toolkit. In: Proceedings of the ACL Interactive Poster and Demonstration Sessions, pp. 214\u2013217. Association for Computational Linguistics, Barcelona, Spain (2004). https:\/\/aclanthology.org\/P04-3031","DOI":"10.3115\/1219044.1219075"},{"key":"7_CR3","unstructured":"Campos, D.F., et al.: MS MARCO: a human generated machine reading comprehension dataset. ArXiv abs\/1611.09268 (2016)"},{"key":"7_CR4","unstructured":"colbertv1.9: https:\/\/huggingface.co\/colbert-ir\/colbertv1.9 (2022)"},{"key":"7_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"7_CR6","unstructured":"Engels, J., Coleman, B., Lakshman, V., Shrivastava, A.: DESSERT: an efficient algorithm for vector set search with vector set queries. In: Thirty-seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=kXfrlWXLwH"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Formal, T., Lassance, C., Piwowarski, B., Clinchant, S.: From distillation to hard negative sampling: making sparse neural IR models more effective. SIGIR (2022)","DOI":"10.1145\/3477495.3531857"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Formal, T., Piwowarski, B., Clinchant, S.: SPLADE: sparse lexical and expansion model for first stage ranking. SIGIR (2021)","DOI":"10.1145\/3404835.3463098"},{"key":"7_CR9","unstructured":"Gumbel, E.: Statistical Theory of Extreme Values and Some Practical Applications: A Series of Lectures. U.S. Government Printing Office, Applied mathematics series (1954)"},{"key":"7_CR10","unstructured":"Jang, E., Gu, S.S., Poole, B.: Categorical reparameterization with Gumbel-Softmax. ICLR (2017)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Khashabi, D., Ng, A., Khot, T., Sabharwal, A., Hajishirzi, H., Callison-Burch, C.: GooAQ: open question answering with diverse answer types (2021). https:\/\/arxiv.org\/abs\/2104.08727","DOI":"10.18653\/v1\/2021.findings-emnlp.38"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Khattab, O., Zaharia, M.A.: ColBERT: efficient and effective passage search via contextualized late interaction over BERT. SIGIR (2020)","DOI":"10.1145\/3397271.3401075"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Lassance, C., Clinchant, S.: The tale of two MSMARCO - and their unfair comparisons. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2431\u20132435. SIGIR \u201923, ACM, New York, NY, USA (2023)","DOI":"10.1145\/3539618.3592071"},{"key":"7_CR14","doi-asserted-by":"publisher","unstructured":"Lassance, C., Maachou, M., Park, J., Clinchant, S.: Learned token pruning in contextualized late interaction over BERT (ColBERT). In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2232\u20132236. SIGIR \u201922, Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3477495.3531835","DOI":"10.1145\/3477495.3531835"},{"key":"7_CR15","unstructured":"Lee, J., et al.: Rethinking the role of token retrieval in multi-vector retrieval. In: Thirty-seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=ZQzm0Z47jz"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: CITADEL: conditional token interaction via dynamic lexical routing for efficient and effective multi-vector retrieval, pp. 11891\u201311907 (2023)","DOI":"10.18653\/v1\/2023.acl-long.663"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., Xiao, S., Shao, Y., Cao, Z.: RetroMAE-2: duplex masked auto-encoder for pre-training retrieval-oriented language models. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2635\u20132648. Association for Computational Linguistics, Toronto, Canada (2023)","DOI":"10.18653\/v1\/2023.acl-long.148"},{"key":"7_CR18","unstructured":"Maddison, C.J., Mnih, A., Teh, Y.W.: The concrete distribution: a continuous relaxation of discrete random variables. ICLR (2017)"},{"key":"7_CR19","unstructured":"MiniLM-L-6-v2: https:\/\/huggingface.co\/cross-encoder\/ms-marco-minilm-l-6-v2 (2022)"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Nardini, F.M., Rulli, C., Venturini, R.: Efficient multi-vector dense retrieval with bit vectors. In: Goharian, N., Tonellotto, N., He, Y., Lipani, A., McDonald, G., Macdonald, C., Ounis, I. (eds.) Advances in Information Retrieval (ECIR 2024), pp. 3\u201317. Springer Nature Switzerland, Cham (2024)","DOI":"10.1007\/978-3-031-56060-6_1"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Ren, R., et al.: RocketQAv2: a joint training method for dense passage retrieval and passage re-ranking. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 2825\u20132835. ACM, Online and Punta Cana, Dominican Republic (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.224"},{"key":"7_CR22","unstructured":"Sang, E.F.T.K., Buchholz, S.: Introduction to the CoNLL-2000 shared task: Chunking (2000). https:\/\/arxiv.org\/abs\/cs\/0009008"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Santhanam, K., Khattab, O., Saad-Falcon, J., Potts, C., Zaharia, M.A.: ColBERTv2: effective and efficient retrieval via lightweight late interaction. ArXiv abs\/2112.01488 (2021)","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"7_CR24","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. CIKM \u201922 (2022)","DOI":"10.1145\/3511808.3557325"},{"key":"7_CR25","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. ACL (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.496"},{"key":"7_CR26","unstructured":"Thakur, N., Reimers, N., R\u00fcckl\u00e9, A., Srivastava, A., Gurevych, I.: BEIR: a heterogeneous benchmark for zero-shot evaluation of information retrieval models. In: NeurIPS (2021)"},{"key":"7_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need (2023). https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Yang, Y., Qiao, Y., He, S., Yang, T.: Weighted KL-divergence for document ranking model refinement. arxiv and SIGIR 2024 (2024)","DOI":"10.1145\/3626772.3657946"}],"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\/978-3-031-88708-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T11:51:57Z","timestamp":1743767517000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-88708-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031887079","9783031887086"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-88708-6_7","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"}}]}}