{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T05:29:34Z","timestamp":1778304574422,"version":"3.51.4"},"reference-count":36,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T00:00:00Z","timestamp":1728345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Web"],"published-print":{"date-parts":[[2024,11,30]]},"abstract":"<jats:p>Rapid response, namely, low latency, is fundamental in search applications; it is particularly so in interactive search sessions, such as those encountered in conversational settings. An observation with a potential to reduce latency asserts that conversational queries exhibit a temporal locality in the lists of documents retrieved. Motivated by this observation, we propose and evaluate a client-side document embedding cache, improving the responsiveness of conversational search systems. By leveraging state-of-the-art dense retrieval models to abstract document and query semantics, we cache the embeddings of documents retrieved for a topic introduced in the conversation, as they are likely relevant to successive queries. Our document embedding cache implements an efficient metric index, answering nearest-neighbor similarity queries by estimating the approximate result sets returned. We demonstrate the efficiency achieved using our cache via reproducible experiments based on Text Retrieval Conference Conversational Assistant Track datasets, achieving a hit rate of up to 75% without degrading answer quality. Our achieved high cache hit rates significantly improve the responsiveness of conversational systems while likewise reducing the number of queries managed on the search back-end.<\/jats:p>","DOI":"10.1145\/3578519","type":"journal-article","created":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T12:04:17Z","timestamp":1672315457000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Caching Historical Embeddings in Conversational Search"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5076-8171","authenticated-orcid":false,"given":"Ophir","family":"Frieder","sequence":"first","affiliation":[{"name":"Georgetown University, Washington, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3730-6383","authenticated-orcid":false,"given":"Ida","family":"Mele","sequence":"additional","affiliation":[{"name":"ISTI CNR, Pisa, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5265-1831","authenticated-orcid":false,"given":"Cristina Ioana","family":"Muntean","sequence":"additional","affiliation":[{"name":"ISTI CNR, Pisa, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3183-334X","authenticated-orcid":false,"given":"Franco Maria","family":"Nardini","sequence":"additional","affiliation":[{"name":"ISTI CNR, Pisa, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7189-4724","authenticated-orcid":false,"given":"Raffaele","family":"Perego","sequence":"additional","affiliation":[{"name":"ISTI CNR, Pisa, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7427-1001","authenticated-orcid":false,"given":"Nicola","family":"Tonellotto","sequence":"additional","affiliation":[{"name":"University of Pisa, Pisa, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,8]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"Dagstuhl Reports","author":"Anand Avishek","year":"2020","unstructured":"Avishek Anand, Lawrence Cavedon, Hideo Joho, Mark Sanderson, and Benno Stein. 2020. Conversational search. In Dagstuhl Reports, Vol. 9."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2645710.2645741"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/1559795.1559815"},{"key":"e_1_3_2_5_2","first-page":"1985","volume-title":"Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201920)","author":"Dalton Jeffrey","year":"2020","unstructured":"Jeffrey Dalton, Chenyan Xiong, Vaibhav Kumar, and Jamie Callan. 2020. CAsT-19: A dataset for conversational information seeking. In Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201920). 1985\u20131988."},{"key":"e_1_3_2_6_2","volume-title":"Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL\u201919)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL\u201919)."},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1145\/1458469.1458473","volume-title":"Proceedings of the Large-Scale Distributed Systems and Information Retrieval Workshop (LSDS-IR\u201908)","author":"Falchi Fabrizio","year":"2008","unstructured":"Fabrizio Falchi, Claudio Lucchese, Salvatore Orlando, Raffaele Perego, and Fausto Rabitti. 2008. A metric cache for similarity search. In Proceedings of the Large-Scale Distributed Systems and Information Retrieval Workshop (LSDS-IR\u201908). 43\u201350."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/1516360.1516450"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2010.12.006"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Jianfeng Gao Chenyan Xiong Paul Bennett and Nick Craswell. 2022. Neural Approaches to Conversational Information Retrieval. Retrieved from https:\/\/arxiv.org\/abs\/2201.05176. DOI:10.48550\/ARXIV.2201.05176","DOI":"10.48550\/ARXIV.2201.05176"},{"key":"e_1_3_2_11_2","doi-asserted-by":"crossref","first-page":"2553","DOI":"10.1145\/3394486.3403305","volume-title":"Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD\u201920)","author":"Huang Jui-Ting","year":"2020","unstructured":"Jui-Ting Huang, Ashish Sharma, Shuying Sun, Li Xia, David Zhang, Philip Pronin, Janani Padmanabhan, Giuseppe Ottaviano, and Linjun Yang. 2020. Embedding-based retrieval in facebook search. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD\u201920). 2553\u20132561."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_14_2","first-page":"39","volume-title":"Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201920)","author":"Khattab Omar","year":"2020","unstructured":"Omar Khattab and Matei Zaharia. 2020. ColBERT: Efficient and effective passage search via contextualized late interaction over BERT. In Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201920). 39\u201348."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.354"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3498557"},{"key":"e_1_3_2_17_2","unstructured":"Jimmy Lin Rodrigo Nogueira and Andrew Yates. 2020. Pretrained Transformers for Text Ranking: BERT and Beyond. Retrieved from https:\/\/arXiv:2010.06467."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3446426"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413557"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102682"},{"issue":"3","key":"e_1_3_2_21_2","article-title":"Topical result caching in web search engines","volume":"57","author":"Mele Ida","year":"2020","unstructured":"Ida Mele, Nicola Tonellotto, Ophir Frieder, and Raffaele Perego. 2020. Topical result caching in web search engines. Info. Proc. Man. 57, 3 (2020).","journal-title":"Info. Proc. Man."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3126368"},{"key":"e_1_3_2_23_2","first-page":"1926","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201915)","author":"Neyshabur Behnam","year":"2015","unstructured":"Behnam Neyshabur and Nathan Srebro. 2015. On symmetric and asymmetric LSHs for inner product search. In Proceedings of the International Conference on Machine Learning (ICML\u201915). 1926\u20131934."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401110"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2844983"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441748"},{"issue":"86","key":"e_1_3_2_28_2","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten Laurens van der","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 86 (2008), 2579\u20132605.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401130"},{"key":"e_1_3_2_30_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201921)","author":"Xiong Lee","year":"2021","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate nearest-neighbor negative contrastive learning for dense text retrieval. In Proceedings of the International Conference on Learning Representations (ICLR\u201921)."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.463"},{"key":"e_1_3_2_32_2","volume-title":"Proceedings of the Text Retrieval Conference (TREC\u201919)","author":"Yang Jheng-Hong","year":"2019","unstructured":"Jheng-Hong Yang, Sheng-Chieh Lin, Chuan-Ju Wang, Jimmy J. Lin, and Ming-Feng Tsai. 2019. Query and answer expansion from conversation history. In Proceedings of the Text Retrieval Conference (TREC\u201919)."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401323"},{"key":"e_1_3_2_34_2","first-page":"829","volume-title":"Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201921)","author":"Yu Shi","year":"2021","unstructured":"Shi Yu, Zhenghao Liu, Chenyan Xiong, Tao Feng, and Zhiyuan Liu. 2021. Few-shot conversational dense retrieval. In Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201921). 829\u2013838."},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Hamed Zamani Johanne R. Trippas Jeff Dalton and Filip Radlinski. 2022. Conversational information seeking. Retrieved from https:\/\/arXiv:2201.08808.","DOI":"10.1561\/9781638282013"},{"key":"e_1_3_2_36_2","first-page":"1503","volume-title":"Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201921)","author":"Zhan Jingtao","year":"2021","unstructured":"Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, and Shaoping Ma. 2021. Optimizing dense retrieval model training with hard negatives. In Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201921). 1503\u20131512."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271776"}],"container-title":["ACM Transactions on the Web"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578519","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3578519","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:37Z","timestamp":1750183717000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578519"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,8]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,11,30]]}},"alternative-id":["10.1145\/3578519"],"URL":"https:\/\/doi.org\/10.1145\/3578519","relation":{},"ISSN":["1559-1131","1559-114X"],"issn-type":[{"value":"1559-1131","type":"print"},{"value":"1559-114X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,8]]},"assertion":[{"value":"2022-06-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}