{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T17:57:05Z","timestamp":1791827825980,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"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":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657891","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"2038-2048","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["ChroniclingAmericaQA: A Large-scale Question Answering Dataset based on Historical American Newspaper Pages"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3578-2393","authenticated-orcid":false,"given":"Bhawna","family":"Piryani","sequence":"first","affiliation":[{"name":"University of Innsbruck, Innsbruck, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4850-9239","authenticated-orcid":false,"given":"Jamshid","family":"Mozafari","sequence":"additional","affiliation":[{"name":"University of Innsbruck, Innsbruck, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7235-0665","authenticated-orcid":false,"given":"Adam","family":"Jatowt","sequence":"additional","affiliation":[{"name":"University of Innsbruck, Innsbruck, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"175","article-title":"OCR Error Correction Using Statistical Machine","volume":"7","author":"Afli Haithem","year":"2016","unstructured":"Haithem Afli, Lo\"ic Barrault, and Holger Schwenk. 2016. OCR Error Correction Using Statistical Machine Translation. Int. J. Comput. Linguistics Appl. , Vol. 7, 1 (2016), 175--191.","journal-title":"Translation. Int. J. Comput. Linguistics Appl."},{"key":"e_1_3_2_1_2_1","unstructured":"Payal Bajaj Daniel Campos Nick Craswell Li Deng Jianfeng Gao Xiaodong Liu Rangan Majumder Andrew McNamara Bhaskar Mitra Tri Nguyen et al. 2016. Ms marco: A human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268 (2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030--45442--5_13"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1389"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18--3403"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.170"},{"key":"e_1_3_2_1_7_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JCDL.2017.7991582"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1108\/09504120710821875"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-023-00345--6"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19--1423"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1123"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604931"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58219-7_21"},{"key":"e_1_3_2_1_15_1","unstructured":"Zishan Guo Renren Jin Chuang Liu Yufei Huang Dan Shi Linhao Yu Yan Liu Jiaxuan Li Bojian Xiong Deyi Xiong et al. 2023. Evaluating Large Language Models: A Comprehensive Survey. arXiv preprint arXiv:2310.19736 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324922000110"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, Yuji Matsumoto and Rashmi Prasad (Eds.). The COLING 2016 Organizing Committee","author":"Hardmeier Christian","year":"2016","unstructured":"Christian Hardmeier. 2016. A Neural Model for Part-of-Speech Tagging in Historical Texts. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, Yuji Matsumoto and Rashmi Prasad (Eds.). The COLING 2016 Organizing Committee, Osaka, Japan, 922--931. https:\/\/aclanthology.org\/C16--1088"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.268"},{"key":"e_1_3_2_1_19_1","volume-title":"2019 ACM\/IEEE Joint Conference on Digital Libraries (JCDL). IEEE, 29--38","author":"Jatowt Adam","year":"2019","unstructured":"Adam Jatowt, Mickael Coustaty, Nhu-Van Nguyen, Antoine Doucet, et al. 2019. Deep statistical analysis of OCR errors for effective post-OCR processing. In 2019 ACM\/IEEE Joint Conference on Digital Libraries (JCDL). IEEE, 29--38."},{"key":"e_1_3_2_1_20_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al.","author":"Jiang Albert Q","year":"2024","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al. 2024. Mixtral of Experts. arXiv preprint arXiv:2401.04088 (2024)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00023"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","unstructured":"Laura Korkeam\u00e4ki and Sanna Kumpulainen. 2019. Interacting with Digital Documents : A Real Life Study of Historians' Task Processes Actions and Goals. https:\/\/doi.org\/10.1145\/3295750.3298931","DOI":"10.1145\/3295750.3298931"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W15-0711"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.211"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412767"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449892"},{"key":"e_1_3_2_1_29_1","volume-title":"Learning Question Classifiers. In COLING 2002: The 19th International Conference on Computational Linguistics. https:\/\/aclanthology.org\/C02--1150","author":"Li Xin","year":"2002","unstructured":"Xin Li and Dan Roth. 2002. Learning Question Classifiers. In COLING 2002: The 19th International Conference on Computational Linguistics. https:\/\/aclanthology.org\/C02--1150"},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Machine Learning. PMLR, 13604--13622","author":"Liska Adam","year":"2022","unstructured":"Adam Liska, Tomas Kocisky, Elena Gribovskaya, Tayfun Terzi, Eren Sezener, Devang Agrawal, D'Autume Cyprien De Masson, Tim Scholtes, Manzil Zaheer, Susannah Young, et al. 2022. Streamingqa: A benchmark for adaptation to new knowledge over time in question answering models. In International Conference on Machine Learning. PMLR, 13604--13622."},{"key":"e_1_3_2_1_31_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. ArXiv","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. ArXiv , Vol. abs\/1907.11692 (2019). https:\/\/api.semanticscholar.org\/CorpusID:198953378"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.bea-1.18"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555400.1555437"},{"key":"e_1_3_2_1_34_1","volume-title":"A survey on multi-hop question answering and generation. arXiv preprint arXiv:2204.09140","author":"Mavi Vaibhav","year":"2022","unstructured":"Vaibhav Mavi, Anubhav Jangra, and Adam Jatowt. 2022. A survey on multi-hop question answering and generation. arXiv preprint arXiv:2204.09140 (2022)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04257-8_1"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16--1028"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453476"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1241"},{"key":"e_1_3_2_1_39_1","volume-title":"Recent Advances in Neural Question Generation. arxiv","author":"Pan Liangming","year":"1905","unstructured":"Liangming Pan, Wenqiang Lei, Tat-Seng Chua, and Min-Yen Kan. 2019. Recent Advances in Neural Question Generation. arxiv: 1905.08949 [cs.CL]"},{"key":"e_1_3_2_1_40_1","volume-title":"LatinX in AI Workshop at ICML 2023 (Regular Deadline). https:\/\/openreview.net\/forum?id=EOOtS6iSE0","author":"Penteado Maria Carolina","year":"2023","unstructured":"Maria Carolina Penteado and F\u00e1bio Perez. 2023. Evaluating GPT-3.5 and GPT-4 on Grammatical Error Correction for Brazilian Portuguese. In LatinX in AI Workshop at ICML 2023 (Regular Deadline). https:\/\/openreview.net\/forum?id=EOOtS6iSE0"},{"key":"e_1_3_2_1_41_1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research, Vol. 21, 140 (2020), 1--67. http:\/\/jmlr.org\/papers\/v21\/20-074.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_42_1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2019","unstructured":"Colin Raffel, Noam M. Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2019. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. J. Mach. Learn. Res. , Vol. 21 (2019), 140:1--140:67. https:\/\/api.semanticscholar.org\/CorpusID:204838007","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2113"},{"key":"e_1_3_2_1_46_1","unstructured":"Evan Sandhaus. 2008. The New York Times Annotated Corpus. https:\/\/doi.org\/11272.1\/AB2\/GZC6PL"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00347"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227833"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1063"},{"key":"e_1_3_2_1_50_1","volume-title":"Yee Whye Teh, and Jonathan Richard Schwarz","author":"Tack Jihoon","year":"2024","unstructured":"Jihoon Tack, Jaehyung Kim, Eric Mitchell, Jinwoo Shin, Yee Whye Teh, and Jonathan Richard Schwarz. 2024. Online Adaptation of Language Models with a Memory of Amortized Contexts. arXiv preprint arXiv:2403.04317 (2024)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","unstructured":"Nina Tahmasebi Lars Borin Adam Jatowt Yang Xu and Simon Hengchen (Eds.). 2021. Computational approaches to semantic change. Number 6 in Language Variation. Language Science Press Berlin. https:\/\/doi.org\/10.5281\/zenodo.5040241","DOI":"10.5281\/zenodo.5040241"},{"key":"e_1_3_2_1_52_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17--2623"},{"key":"e_1_3_2_1_54_1","volume-title":"Assessing the Impact of OCR Quality on Downstream NLP Tasks. In International Conference on Agents and Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:215756646","author":"van Strien Daniel Alexander","year":"2020","unstructured":"Daniel Alexander van Strien, Kaspar Beelen, Mariona Coll Ardanuy, Kasra Hosseini, Barbara McGillivray, and Giovanni Colavizza. 2020. Assessing the Impact of OCR Quality on Downstream NLP Tasks. In International Conference on Agents and Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:215756646"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531734"},{"key":"e_1_3_2_1_56_1","volume-title":"Manning","author":"Yang Zhilin","year":"2018","unstructured":"Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering. CoRR , Vol. abs\/1809.09600 (2018). showeprint[arXiv]1809.09600 http:\/\/arxiv.org\/abs\/1809.09600"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.611"},{"key":"e_1_3_2_1_58_1","volume-title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension. CoRR","author":"Zhang Sheng","year":"2018","unstructured":"Sheng Zhang, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Kevin Duh, and Benjamin Van Durme. 2018. ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension. CoRR , Vol. abs\/1810.12885 (2018). showeprint[arXiv]1810.12885 http:\/\/arxiv.org\/abs\/1810.12885"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657891","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657891","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:38:33Z","timestamp":1755841113000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657891"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":58,"alternative-id":["10.1145\/3626772.3657891","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657891","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}