{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:16:18Z","timestamp":1743124578450,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819617098"},{"type":"electronic","value":"9789819617104"}],"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\/978-981-96-1710-4_6","type":"book-chapter","created":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T09:56:59Z","timestamp":1738317419000},"page":"66-79","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring the\u00a0Potential of\u00a0Dimension Reduction in\u00a0Building Efficient Dense Retrieval Systems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3671-5978","authenticated-orcid":false,"given":"Zhipeng","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0083-3224","authenticated-orcid":false,"given":"Zhenghao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7422-6254","authenticated-orcid":false,"given":"Yu","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3171-8889","authenticated-orcid":false,"given":"Ge","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,1]]},"reference":[{"key":"6_CR1","unstructured":"Bengio, Y., L\u00e9onard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprintarXiv:1308.3432 (2013)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: BGE M3-Embedding: multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Gao, L., Callan, J.: Condenser: a pre-training architecture for dense retrieval. In: Proceedings of EMNLP, pp. 981\u2013993 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.75"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Gao, L., Callan, J.: Unsupervised corpus aware language model pre-training for dense passage retrieval. In: Proceedings of ACL, pp. 2843\u20132853 (2022)","DOI":"10.18653\/v1\/2022.acl-long.203"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Indyk,P., Motwani, R.: Approximate nearest neighbors: towards removing the curse of dimensionality. In: Proceedings ACM STOC, pp. 604\u2013613 (1998)","DOI":"10.1145\/276698.276876"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Izacard, G., Grave, \u00c9.: Leveraging passage retrieval with generative models for open domain question answering. In: Proceedings of EACL, pp. 874\u2013880 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"issue":"1","key":"6_CR7","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H J\u00e9gou","year":"2011","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE Trans. Pattern Anal. Mach. Intell. 33(1), 117\u2013128 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"6_CR8","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":"6_CR9","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: Proceedings of EMNLP, pp. 6769\u20136781 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"6_CR10","first-page":"452","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, 452\u2013466 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"6_CR11","unstructured":"Lewis, M., et al.: Pre-training via paraphrasing. In: Proceedings of NeurIPS (2020)"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: LibVQ: a toolkit for optimizing vector quantization and efficient neural retrieval. In: Proceedings of SIGIR, pp. 3095\u20133099 (2023)","DOI":"10.1145\/3539618.3591799"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: More robust dense retrieval with contrastive dual learning. In: Proceedings of SIGIR ICTIR, pp. 287\u2013296 (2021)","DOI":"10.1145\/3471158.3472245"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Adapting open domain fact extraction and verification to COVID-fact through in-domain language modeling. In: Findings of ACL, pp. 2395\u20132400 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.216"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Dimension reduction for efficient dense retrieval via conditional autoencoder. In: Proceedings of EMNLP, pp. 5692\u20135698 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.384"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Fine-grained fact verification with kernel graph attention network. In: Proceedings of ACL, pp. 7342\u20137351 (2020)","DOI":"10.18653\/v1\/2020.acl-main.655"},{"issue":"2","key":"6_CR17","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"S Lloyd","year":"1982","unstructured":"Lloyd, S.: Least squares quantization in PCM. IEEE Trans. Inf. Theory 28(2), 129\u2013137 (1982)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Ma, X., et al.: Simple and effective unsupervised redundancy elimination to compress dense vectors for passage retrieval. In: Proceedings of the EMNLP, pp. 2854\u20132859 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.227"},{"key":"6_CR19","unstructured":"MacQueen, J., et\u00a0al.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, vol.\u00a01, pp. 281\u2013297. Oakland, CA, USA (1967)"},{"issue":"4","key":"6_CR20","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/TPAMI.2018.2889473","volume":"42","author":"YA Malkov","year":"2018","unstructured":"Malkov, Y.A.: Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE Trans. Pattern Anal. Mach. Intell. 42(4), 824\u2013836 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"McKusick, M.K., et al.: A fast file system for UNIX. ACM Trans. Comput. Syst. 2(3), 181\u2013197 (1984)","DOI":"10.1145\/989.990"},{"issue":"2","key":"6_CR22","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1006\/inco.1993.1057","volume":"106","author":"S Meiser","year":"1993","unstructured":"Meiser, S.: Point location in arrangements of hyperplanes. Inf. Comput. 106(2), 286\u2013303 (1993)","journal-title":"Inf. Comput."},{"key":"6_CR23","unstructured":"Min, S., et al.: NeurIPS 2020 efficientQA competition: Systems, analyses and lessons learned. In: Proceedings of the NeurIPS 2020 Competition and Demonstration Track, pp. 86\u2013111 (2021)"},{"key":"6_CR24","unstructured":"Nguyen, T., et al.: MS MARCO: a human generated machine reading comprehension dataset. In: Proceedings of NIPS, vol. 1773 (2016)"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Ni, J., et al.: Large dual encoders are generalizable retrievers. In: Proceedings of EMNLP, pp. 9844\u20139855 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.669"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: The curse of dense low-dimensional information retrieval for large index sizes. In: Proceedings of ACL, pp. 605\u2013611 (2021)","DOI":"10.18653\/v1\/2021.acl-short.77"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Salton, G., Fox, E.A., Wu, H.: Extended Boolean information retrieval. Commun. ACM 26(11), 1022\u20131036 (1983)","DOI":"10.1145\/182.358466"},{"key":"6_CR28","unstructured":"Thakur, N., et al.: BEIR: a heterogeneous benchmark for zero-shot evaluation of information retrieval models. In: NeurIPS Datasets and Benchmarks Track (2021)"},{"key":"6_CR29","unstructured":"Xiao, S., et al.: C-Pack: packaged resources to advance general Chinese embedding. arXiv preprint arXiv:2309.07597 (2023)"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Xiao, S., et al.: Distill-VQ: learning retrieval oriented vector quantization by distilling knowledge from dense embeddings. In: Proceedings of SIGIR, pp. 1513\u20131523 (2022)","DOI":"10.1145\/3477495.3531799"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Xiao, S., et al.: Matching-oriented embedding quantization for ad-hoc retrieval. In: Proceedings of EMNLP, pp. 8119\u20138129 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.640"},{"key":"6_CR32","unstructured":"Xiong, L., et al.: Approximate nearest neighbor negative contrastive learning for dense text retrieval. In: Processing of ICLR (2020)"},{"key":"6_CR33","unstructured":"Xiong, W., et al.: Answering complex open-domain questions with multi-hop dense retrieval. In: Processing of ICLR (2020)"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Yamada, I., Asai, A., Hajishirzi, H.: Efficient passage retrieval with hashing for open-domain question answering. In: Proceedings of ACL, pp. 979\u2013986 (2021)","DOI":"10.18653\/v1\/2021.acl-short.123"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Yang, S., Seo, M.: Designing a minimal retrieve-and-read system for open-domain question answering. In: Proceedings of NAACL-HLT, pp. 5856\u20135865 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.468"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Yu, S., et al.: Few-shot conversational dense retrieval. In: Proceedings of SIGIR, pp. 829\u2013838 (2021)","DOI":"10.1145\/3404835.3462856"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Zhan, J., et al.: Jointly optimizing query encoder and product quantization to improve retrieval performance. In: Proceedings of CIKM, pp. 2487\u20132496 (2021)","DOI":"10.1145\/3459637.3482358"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Zhan, J., et al.: Optimizing dense retrieval model training with hard negatives. In: Proceedings of SIGIR, pp. 1503\u20131512 (2021)","DOI":"10.1145\/3404835.3462880"},{"key":"6_CR39","unstructured":"Zhao, W.X. et al.: Dense text retrieval based on pretrained language models: a survey. arXiv preprint arXiv:2211.14876 (2022)"},{"issue":"2","key":"6_CR40","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1145\/1132956.1132959","volume":"38","author":"J Zobel","year":"2006","unstructured":"Zobel, J., Moffat, A.: Inverted files for text search engines. ACM Comput. Surv. 38(2), 6 (2006)","journal-title":"ACM Comput. Surv."}],"container-title":["Lecture Notes in Computer Science","Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1710-4_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T09:57:20Z","timestamp":1738317440000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1710-4_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819617098","9789819617104"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1710-4_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccir2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cips-ir.org.cn\/CCIR2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}