{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:06:06Z","timestamp":1750309566338,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Nouvelle-Aquitaine Region (France)","award":["2019-1R40226"],"award-info":[{"award-number":["2019-1R40226"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,16]]},"DOI":"10.1145\/3677389.3702542","type":"proceedings-article","created":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T16:53:52Z","timestamp":1741884832000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Retrieval Augmented Generation for Historical Newspapers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1261-950X","authenticated-orcid":false,"given":"The Trung","family":"Tran","sequence":"first","affiliation":[{"name":"University of Science and Technology of Hanoi, Hanoi, Viet Nam"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0787-2990","authenticated-orcid":false,"given":"Carlos-Emiliano","family":"Gonz\u00e1lez-Gallardo","sequence":"additional","affiliation":[{"name":"LIFAT \/ CESR, University of TOURS, Tours, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6160-3356","authenticated-orcid":false,"given":"Antoine","family":"Doucet","sequence":"additional","affiliation":[{"name":"University of La Rochelle, La Rochelle, France"}]}],"member":"320","published-online":{"date-parts":[[2025,3,13]]},"reference":[{"unstructured":"Emanuela Boros Carlos-Emiliano Gonz\u00e1lez-Gallardo Edward Giamphy Ahmed Hamdi Jos\u00e9 G Moreno and Antoine Doucet. 2022. Knowledge-based Contexts for Historical Named Entity Recognition & Linking.. In CLEF (Working Notes). 1064--1078.","key":"e_1_3_2_1_1_1"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval. 335--336","author":"Carbonell Jaime","year":"1998","unstructured":"Jaime Carbonell and Jade Goldstein. 1998. The use of MMR, diversity-based reranking for reordering documents and producing summaries. In Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval. 335--336."},{"volume-title":"Crowdsourcing our cultural heritage","author":"Causer Tim","unstructured":"Tim Causer and Melissa Terras. 2016. 'Many Hands Make Light Work. Many Hands Together Make Merry Work'1: Transcribe Bentham and Crowdsourcing Manuscript Collections. In Crowdsourcing our cultural heritage. Routledge, 57--88.","key":"e_1_3_2_1_3_1"},{"key":"e_1_3_2_1_4_1","volume-title":"15th Annual International Conference of the Alliance of Digital Humanities Organizations, DH","author":"Doucet Antoine","year":"2020","unstructured":"Antoine Doucet, Martin Gasteiner, Mark Granroth-Wilding, Max Kaiser, Minna Kaukonen, Roger Labahn, Jean-Philippe Moreux, G\u00fcnter M\u00fchlberger, Eva Pfanzelter, Marie-Eve Therenty, Hannu Toivonen, and Mikko Tolonen. 2020. News-Eye: A digital investigator for historical newspapers. In 15th Annual International Conference of the Alliance of Digital Humanities Organizations, DH 2020, Ottawa, Canada, July 20--25, 2020, Conference Abstracts, Laura Estill and Jennifer Guiliano (Eds.). https:\/\/dh2020.adho.org\/wp-content\/uploads\/2020\/07\/721_NewsEyeAdigitalinvestigatorforhistoricalnewspapers.html"},{"key":"e_1_3_2_1_5_1","volume-title":"RIGHT: Retrieval-Augmented Generation for Mainstream Hashtag Recommendation. In European Conference on Information Retrieval. Springer, 39--55","author":"Fan Run-Ze","year":"2024","unstructured":"Run-Ze Fan, Yixing Fan, Jiangui Chen, Jiafeng Guo, Ruqing Zhang, and Xueqi Cheng. 2024. RIGHT: Retrieval-Augmented Generation for Mainstream Hashtag Recommendation. In European Conference on Information Retrieval. Springer, 39--55."},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Asian Digital Libraries. Springer, 76--88","author":"Girdhar Nancy","year":"2023","unstructured":"Nancy Girdhar, Micka\u00ebl Coustaty, and Antoine Doucet. 2023. Benchmarking nas for article separation in historical newspapers. In International Conference on Asian Digital Libraries. Springer, 76--88."},{"key":"e_1_3_2_1_7_1","volume-title":"European Conference on Information Retrieval. Springer, 377--393","author":"Gonz\u00e1lez-Gallardo Carlos-Emiliano","year":"2023","unstructured":"Carlos-Emiliano Gonz\u00e1lez-Gallardo, Emanuela Boros, Edward Giamphy, Ahmed Hamdi, Jos\u00e9 G Moreno, and Antoine Doucet. 2023. Injecting temporal-aware knowledge in historical named entity recognition. In European Conference on Information Retrieval. Springer, 377--393."},{"key":"e_1_3_2_1_8_1","volume-title":"2023 ACM\/IEEE Joint Conference on Digital Libraries (JCDL). IEEE, 184--189","author":"Gonz\u00e1lez-Gallardo Carlos-Emiliano","year":"2023","unstructured":"Carlos-Emiliano Gonz\u00e1lez-Gallardo, Emanuela Boros, Nancy Girdhar, Ahmed Hamdi, Jose G Moreno, and Antoine Doucet. 2023. Yes but.. can chatgpt identify entities in historical documents?. In 2023 ACM\/IEEE Joint Conference on Digital Libraries (JCDL). IEEE, 184--189."},{"key":"e_1_3_2_1_9_1","volume-title":"Leveraging Open Large Language Models for Historical Named Entity Recognition. In The 28th International Conference on Theory and Practice of Digital Libraries","author":"Gonz\u00e1lez-Gallardo Carlos-Emiliano","year":"2024","unstructured":"Carlos-Emiliano Gonz\u00e1lez-Gallardo, Tran Thi Hong Hanh, Ahmed Hamdi, and Antoine Doucet. 2024. Leveraging Open Large Language Models for Historical Named Entity Recognition. In The 28th International Conference on Theory and Practice of Digital Libraries. Ljubljana, Slovenia. https:\/\/univ-rochelle.hal.science\/hal-04662000"},{"key":"e_1_3_2_1_10_1","volume-title":"Query expansion by prompting large language models. arXiv preprint arXiv:2305.03653","author":"Jagerman Rolf","year":"2023","unstructured":"Rolf Jagerman, Honglei Zhuang, Zhen Qin, Xuanhui Wang, and Michael Bendersky. 2023. Query expansion by prompting large language models. arXiv preprint arXiv:2305.03653 (2023)."},{"key":"e_1_3_2_1_11_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020), 9459--9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_12_1","volume-title":"Query rewriting for retrieval-augmented large language models. arXiv preprint arXiv:2305.14283","author":"Ma Xinbei","year":"2023","unstructured":"Xinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao, and Nan Duan. 2023. Query rewriting for retrieval-augmented large language models. arXiv preprint arXiv:2305.14283 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings 2003 international conference on image processing (Cat. No. 03CH37429)","volume":"3","author":"Piella Gemma","year":"2003","unstructured":"Gemma Piella and Henk Heijmans. 2003. A new quality metric for image fusion. In Proceedings 2003 international conference on image processing (Cat. No. 03CH37429), Vol. 3. IEEE, III-173."},{"key":"e_1_3_2_1_14_1","volume-title":"hmbert: Historical multilingual language models for named entity recognition. arXiv preprint arXiv:2205.15575","author":"Schweter Stefan","year":"2022","unstructured":"Stefan Schweter, Luisa M\u00e4rz, Katharina Schmid, and Erion \u00c7ano. 2022. hmbert: Historical multilingual language models for named entity recognition. arXiv preprint arXiv:2205.15575 (2022)."},{"doi-asserted-by":"crossref","unstructured":"Karthik Soman Peter W Rose John H Morris Rabia E Akbas Brett Smith Braian Peetoom Catalina Villouta-Reyes Gabriel Cerono Yongmei Shi Angela Rizk-Jackson Sharat Israni Charlotte A Nelson Sui Huang and Sergio E Baranzini. 2024. Biomedical knowledge graph-optimized prompt generation for large language models. arXiv:2311.17330 [cs.CL] https:\/\/arxiv.org\/abs\/2311.17330","key":"e_1_3_2_1_15_1","DOI":"10.1093\/bioinformatics\/btae560"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1007\/978-94-6091-299-3_1"},{"key":"e_1_3_2_1_17_1","volume-title":"Tsdae: Using transformer-based sequential denoising auto-encoder for unsupervised sentence embedding learning. arXiv preprint arXiv:2104.06979","author":"Wang Kexin","year":"2021","unstructured":"Kexin Wang, Nils Reimers, and Iryna Gurevych. 2021. Tsdae: Using transformer-based sequential denoising auto-encoder for unsupervised sentence embedding learning. arXiv preprint arXiv:2104.06979 (2021)."},{"key":"e_1_3_2_1_18_1","volume-title":"GPL: Generative pseudo labeling for unsupervised domain adaptation of dense retrieval. arXiv preprint arXiv:2112.07577","author":"Wang Kexin","year":"2021","unstructured":"Kexin Wang, Nandan Thakur, Nils Reimers, and Iryna Gurevych. 2021. GPL: Generative pseudo labeling for unsupervised domain adaptation of dense retrieval. arXiv preprint arXiv:2112.07577 (2021)."},{"key":"e_1_3_2_1_19_1","volume-title":"Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675","author":"Zhang Tianyi","year":"2019","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675 (2019)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","first-page":"1114","DOI":"10.1162\/tacl_a_00595","article-title":"Miracl: A multilingual retrieval dataset covering 18 diverse languages","volume":"11","author":"Zhang Xinyu","year":"2023","unstructured":"Xinyu Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, and Jimmy Lin. 2023. Miracl: A multilingual retrieval dataset covering 18 diverse languages. Transactions of the Association for Computational Linguistics 11 (2023), 1114--1131.","journal-title":"Transactions of the Association for Computational Linguistics"}],"event":{"sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","IEEE TCDL"],"acronym":"JCDL '24","name":"JCDL '24: 24th ACM\/IEEE Joint Conference on Digital Libraries","location":"Hong Kong China"},"container-title":["Proceedings of the 24th ACM\/IEEE Joint Conference on Digital Libraries"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677389.3702542","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3677389.3702542","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:19:07Z","timestamp":1750295947000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677389.3702542"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":20,"alternative-id":["10.1145\/3677389.3702542","10.1145\/3677389"],"URL":"https:\/\/doi.org\/10.1145\/3677389.3702542","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]},"assertion":[{"value":"2025-03-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}