{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T22:29:20Z","timestamp":1780439360783,"version":"3.54.1"},"reference-count":53,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T00:00:00Z","timestamp":1716940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2024,5,29]]},"abstract":"<jats:p>Recently, there has been significant interest in extracting actionable insights from the abundance of unstructured textual data. In this paper, we introduce a novel problem, which we term Semistructured Schema and Data Extraction (SDE). This task aims to enhance and complete tables using information discovered from textual repositories, given partial table specifications in the form of queries. To effectively solve SDE, several challenges must be overcome, which involve transforming the partial table specifications into effective queries, retrieving relevant documents, discerning values for partially specified attributes, inferring additional attributes, and constructing an enriched output table while mitigating the influence of false positives from the retrieval.<\/jats:p>\n          <jats:p>We propose an end-to-end pipeline for SDE, which consists of a retrieval component and an augmentation component, to address each of the challenges. In the retrieval component, we serialize the partial table specifications into a query and employ a dense passage retrieval algorithm to extract the top-k relevant results from the text repository. Subsequently, the augmentation component ingests the output documents from the retrieval phase and generates an enriched table. We formulate this table enrichment task as a unique sequence-to-sequence task, distinct from traditional approaches, as it operates on multiple documents during generation. Utilizing an interpolation mechanism on the encoder output, our model maintains a nearly constant context length while automatically prioritizing the importance of documents during the generation.<\/jats:p>\n          <jats:p>Due to the novelty of SDE, we establish a validation methodology, adapting and expanding existing benchmarks with the use of powerful large language models. Our extensive experiments show that our method achieves high accuracy in enriching query tables through multi-document fusion, while also surpassing baseline methods in both accuracy and computational efficiency.<\/jats:p>","DOI":"10.1145\/3654984","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T09:44:53Z","timestamp":1717062293000},"page":"1-26","source":"Crossref","is-referenced-by-count":1,"title":["Unstructured Data Fusion for Schema and Data Extraction"],"prefix":"10.1145","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6724-9870","authenticated-orcid":false,"given":"Kaiwen","family":"Chen","sequence":"first","affiliation":[{"name":"University of Toronto, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5648-0638","authenticated-orcid":false,"given":"Nick","family":"Koudas","sequence":"additional","affiliation":[{"name":"University of Toronto, Toronto, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,30]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582416"},{"key":"e_1_2_1_2_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409","author":"Bahdanau Dzmitry","year":"2015","unstructured":"Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409.0473"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00067"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"e_1_2_1_5_1","volume-title":"Lin (Eds.)","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877--1901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_2_1_6_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.14778\/3397230.3397235"},{"key":"e_1_2_1_8_1","unstructured":"Thomas Davis and Max Kolesnyk. 2023. JSONRESUME-fake. https:\/\/github.com\/jsonresume\/jsonresume-fake Accessed: 2023-09--30."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.14778\/3430915.3430921"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19--1423"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.52"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611479.3611533"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555041.3589409"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2018.00094"},{"key":"e_1_2_1_15_1","volume-title":"Advances in Database Technology: EDBT 2021, 24th International Conference on Extending Database Technology: Nicosia, Cyprus, March 23--26, 2021: proceedings. OpenProceedings, 690--693","author":"de Jes\u00fas Flores Herrera Javier","year":"2021","unstructured":"Javier de Jes\u00fas Flores Herrera, Sergi Nadal Francesch, and \u00d3scar Romero Moral. 2021. Effective and scalable data discovery with NextiaJD. In Advances in Database Technology: EDBT 2021, 24th International Conference on Extending Database Technology: Nicosia, Cyprus, March 23--26, 2021: proceedings. OpenProceedings, 690--693."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.348"},{"key":"e_1_2_1_17_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"4116","author":"Hashimoto Tatsunori","year":"2021","unstructured":"Tatsunori Hashimoto. 2021. Model Performance Scaling with Multiple Data Sources. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 4107--4116. https:\/\/proceedings.mlr.press\/v139\/hashimoto21a.html"},{"key":"e_1_2_1_18_1","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. arxiv: 2106.09685 [cs.CL]"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526049"},{"key":"e_1_2_1_20_1","volume-title":"Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oug uz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588689"},{"key":"e_1_2_1_22_1","volume-title":"Supervised contrastive learning. Advances in neural information processing systems","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in neural information processing systems , Vol. 33 (2020), 18661--18673."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1128"},{"key":"e_1_2_1_24_1","volume-title":"Fabio Petroni and Luke Zettlemoyer","author":"Sebastian Riedel Ledell Wu Martin Josifoski","year":"2020","unstructured":"Martin Josifoski Sebastian Riedel Ledell Wu, Fabio Petroni and Luke Zettlemoyer. 2020. Zero-shot Entity Linking with Dense Entity Retrieval. In EMNLP."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.330"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100017"},{"key":"e_1_2_1_29_1","first-page":"1","article-title":"Practical guidance for using multiple data sources in systematic reviews and meta-analyses (with examples from the MUDS study)","volume":"9","author":"Mayo-Wilson Evan","year":"2017","unstructured":"Evan Mayo-Wilson, Tianjing Li, Nicole Fusco, Kay Dickersin, and MUDS investigators. 2017. Practical guidance for using multiple data sources in systematic reviews and meta-analyses (with examples from the MUDS study). Res Synth Methods, Vol. 9, 1 (Dec. 2017), 2--12.","journal-title":"Res Synth Methods"},{"key":"e_1_2_1_30_1","volume-title":"Neural models for information retrieval. arXiv preprint arXiv:1705.01509","author":"Mitra Bhaskar","year":"2017","unstructured":"Bhaskar Mitra and Nick Craswell. 2017. Neural models for information retrieval. arXiv preprint arXiv:1705.01509 (2017)."},{"key":"e_1_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Marius Mosbach Tiago Pimentel Shauli Ravfogel Dietrich Klakow and Yanai Elazar. 2023. Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation. arxiv: 2305.16938 [cs.CL]","DOI":"10.18653\/v1\/2023.findings-acl.779"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.14778\/3574245.3574258"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5525"},{"key":"e_1_2_1_34_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arxiv: 2303.08774 [cs.CL]"},{"key":"e_1_2_1_35_1","unstructured":"Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray John Schulman Jacob Hilton Fraser Kelton Luke Miller Maddie Simens Amanda Askell Peter Welinder Paul Christiano Jan Leike and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. arxiv: 2203.02155 [cs.CL]"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132914"},{"key":"e_1_2_1_37_1","volume-title":"STable: Table Generation Framework for Encoder-Decoder Models. arXiv preprint arXiv:2206.04045","author":"Pietruszka Micha\u0142","year":"2022","unstructured":"Micha\u0142 Pietruszka, Micha\u0142 Turski, \u0141ukasz Borchmann, Tomasz Dwojak, Gabriela Pa\u0142ka, Karolina Szyndler, Dawid Jurkiewicz, and \u0141ukasz Garncarek. 2022. STable: Table Generation Framework for Encoder-Decoder Models. arXiv preprint arXiv:2206.04045 (2022)."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3049"},{"key":"e_1_2_1_39_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. J. Mach. Learn. Res. , Vol. 21, 1, Article 140 (jan 2020), bibinfonumpages67 pages.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_2_1_41_1","volume-title":"Introduction to information retrieval","author":"Sch\u00fctze Hinrich","unstructured":"Hinrich Sch\u00fctze, Christopher D Manning, and Prabhakar Raghavan. 2008. Introduction to information retrieval. Vol. 39. Cambridge University Press Cambridge."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.71"},{"key":"e_1_2_1_43_1","volume-title":"Sequence to sequence learning with neural networks. Advances in neural information processing systems","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. Advances in neural information processing systems , Vol. 27 (2014)."},{"key":"e_1_2_1_44_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arxiv: 2307.09288 [cs.CL]"},{"key":"e_1_2_1_45_1","first-page":"5","article-title":"Synthesizing Qualitative Data Sets to Improve the Design of Trials and Complex Health Interventions: A Worked Example","volume":"29","author":"Turner Katrina M","year":"2018","unstructured":"Katrina M Turner, John Percival, David Kessler, and Jenny L Donovan. 2018. Synthesizing Qualitative Data Sets to Improve the Design of Trials and Complex Health Interventions: A Worked Example. Qual Health Res, Vol. 29, 5 (Oct. 2018), 693--699.","journal-title":"Qual Health Res"},{"key":"e_1_2_1_46_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1239"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.180"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.451"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.1"},{"key":"e_1_2_1_51_1","volume-title":"BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SkeHuCVFDr","author":"Tianyi","year":"2020","unstructured":"Tianyi Zhang*, Varsha Kishore*, Felix Wu*, Kilian Q. Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SkeHuCVFDr"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517891"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.5"}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654984","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3654984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T14:39:57Z","timestamp":1755787197000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654984"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,29]]},"references-count":53,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,5,29]]}},"alternative-id":["10.1145\/3654984"],"URL":"https:\/\/doi.org\/10.1145\/3654984","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,29]]}}}