{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:56:30Z","timestamp":1776930990256,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3791449","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T05:37:48Z","timestamp":1776058668000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SemTabla: A Human-in-the-Loop Framework for Semantic Enrichment and Validation of Data Tables"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7246-3923","authenticated-orcid":false,"given":"Zhuochen","family":"Jin","sequence":"first","affiliation":[{"name":"Tongji Universiy, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7466-7031","authenticated-orcid":false,"given":"Yingjie","family":"Mi","sequence":"additional","affiliation":[{"name":"School of intelligence Science and Technology, Nanjing University, Nanjing, China and Huawei Cloud, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0886-0128","authenticated-orcid":false,"given":"Yehang","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Intelligent Software and Engineering, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4344-3903","authenticated-orcid":false,"given":"yichen","family":"yao","sequence":"additional","affiliation":[{"name":"School of Intelligent Software and Engineering, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0579-0244","authenticated-orcid":false,"given":"Chongyang","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6481-3770","authenticated-orcid":false,"given":"Ke","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"crossref","unstructured":"Osman Akbulut Lucy McLaughlin Tong Xin Matthew Forshaw and Nicolas\u00a0S Holliman. 2023. Visualizing ordered bivariate data on node-link diagrams. Visual Informatics 7 3 (2023) 22\u201336.","DOI":"10.1016\/j.visinf.2023.06.003"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2723711"},{"key":"e_1_3_3_3_4_2","first-page":"1448","volume-title":"2007 IEEE 23rd international conference on data engineering","author":"Bauckmann Jana","year":"2006","unstructured":"Jana Bauckmann, Ulf Leser, Felix Naumann, and Veronique Tietz. 2006. Efficiently detecting inclusion dependencies. In 2007 IEEE 23rd international conference on data engineering. IEEE, 1448\u20131450."},{"key":"e_1_3_3_3_5_2","unstructured":"Asim Biswal Liana Patel Siddarth Jha Amog Kamsetty Shu Liu Joseph\u00a0E Gonzalez Carlos Guestrin and Matei Zaharia. 2024. Text2sql is not enough: Unifying ai and databases with tag. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.14717 (2024)."},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-45599-0_21"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"crossref","unstructured":"Michelle\u00a0A Borkin Chelsea\u00a0S Yeh Madelaine Boyd Peter Macko Krzysztof\u00a0Z Gajos Margo Seltzer and Hanspeter Pfister. 2013. Evaluation of filesystem provenance visualization tools. IEEE Transactions on Visualization and Computer Graphics 19 12 (2013) 2476\u20132485.","DOI":"10.1109\/TVCG.2013.155"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"crossref","unstructured":"Christian Bors Theresia Gschwandtner and Silvia Miksch. 2019. Capturing and visualizing provenance from data wrangling. IEEE computer graphics and applications 39 6 (2019) 61\u201375.","DOI":"10.1109\/MCG.2019.2941856"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"crossref","unstructured":"Michael Bostock Vadim Ogievetsky and Jeffrey Heer. 2011. D3 data-driven documents. IEEE Transactions on Visualization and Computer Graphics 17 12 (2011) 2301\u20132309.","DOI":"10.1109\/TVCG.2011.185"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"crossref","unstructured":"Xiwen Cai Xiaodong Ge Kai Xiong Shuainan Ye Di Weng Ke Xu Datong Wei Jiang Long and Yingcai Wu. 2025. HYPNOS: Interactive Data Lineage Tracing for Data Transformation Scripts. IEEE Transactions on Visualization and Computer Graphics (2025).","DOI":"10.1109\/TVCG.2025.3552091"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/1142473.1142574"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"crossref","unstructured":"Upol Ehsan and Mark\u00a0O Riedl. 2024. Explainability pitfalls: Beyond dark patterns in explainable AI. Patterns 5 6 (2024).","DOI":"10.1016\/j.patter.2024.100971"},{"key":"e_1_3_3_3_13_2","unstructured":"Mahdi Esmailoghli Jorge-Arnulfo Quian\u00e9-Ruiz and Ziawasch Abedjan. 2021. MATE: multi-attribute table extraction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.00318 (2021)."},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"crossref","unstructured":"Wenwen Gao Shangsong Liu Yi Zhou Fengjie Wang Feng Zhou and Min Zhu. 2024. GBDT4CTRVis: visual analytics of gradient boosting decision tree for advertisement click-through rate prediction. Journal of Visualization 27 4 (2024) 639\u2013659.","DOI":"10.1007\/s12650-024-00984-0"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642497"},{"key":"e_1_3_3_3_16_2","unstructured":"Cynthia\u00a0A Huang. 2023. Visualising category recoding and numeric redistributions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.06535 (2023)."},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"crossref","unstructured":"Yka Huhtala Juha K\u00e4rkk\u00e4inen Pasi Porkka and Hannu Toivonen. 1999. TANE: An efficient algorithm for discovering functional and approximate dependencies. The computer journal 42 2 (1999) 100\u2013111.","DOI":"10.1093\/comjnl\/42.2.100"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"crossref","unstructured":"Hiroshi Iida Dung Thai Varun Manjunatha and Mohit Iyyer. 2021. Tabbie: Pretrained representations of tabular data. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2105.02584 (2021).","DOI":"10.18653\/v1\/2021.naacl-main.270"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"crossref","unstructured":"Lan Jiang and Felix Naumann. 2020. Holistic primary key and foreign key detection. Journal of Intelligent Information Systems 54 3 (2020) 439\u2013461.","DOI":"10.1007\/s10844-019-00562-z"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7596-7_14"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979444"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581001"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"crossref","unstructured":"Julien Klaus Mark Blacher Andreas Goral Philipp Lucas and Joachim Giesen. 2023. A visual analytics workflow for probabilistic modeling. Visual Informatics 7 2 (2023) 72\u201384.","DOI":"10.1016\/j.visinf.2023.05.001"},{"key":"e_1_3_3_3_24_2","unstructured":"Yun-Hsin Kuo Dongyu Liu and Kwan-Liu Ma. 2024. SpreadLine: Visualizing egocentric dynamic influence. IEEE Transactions on Visualization and Computer Graphics (2024)."},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"crossref","unstructured":"Peng Li Yeye He Dror Yashar Weiwei Cui Song Ge Haidong Zhang Danielle Rifinski\u00a0Fainman Dongmei Zhang and Surajit Chaudhuri. 2024. Table-gpt: Table fine-tuned gpt for diverse table tasks. Proceedings of the ACM on Management of Data 2 3 (2024) 1\u201328.","DOI":"10.1145\/3654979"},{"key":"e_1_3_3_3_26_2","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et\u00a0al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.19437 (2024)."},{"key":"e_1_3_3_3_27_2","unstructured":"Xinyu Liu Shuyu Shen Boyan Li Peixian Ma Runzhi Jiang Yuxin Zhang Ju Fan Guoliang Li Nan Tang and Yuyu Luo. 2024. A Survey of NL2SQL with Large Language Models: Where are we and where are we going?arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.05109 (2024)."},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"crossref","unstructured":"Weizheng Lu Jing Zhang Ju Fan Zihao Fu Yueguo Chen and Xiaoyong Du. 2025. Large language model for table processing: A survey. Frontiers of Computer Science 19 2 (2025) 192350.","DOI":"10.1007\/s11704-024-40763-6"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"crossref","unstructured":"Hongjiang Lv Zhibin Niu Wei Han and Xiang Li. 2024. Can GPT embeddings enhance visual exploration of literature datasets? A case study on isostatic pressing research. Journal of Visualization 27 6 (2024) 1213\u20131226.","DOI":"10.1007\/s12650-024-01010-z"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"crossref","unstructured":"Michael\u00a0V Mannino Paicheng Chu and Thomas Sager. 1988. Statistical profile estimation in database systems. ACM Computing Surveys (CSUR) 20 3 (1988) 191\u2013221.","DOI":"10.1145\/62061.62063"},{"key":"e_1_3_3_3_31_2","unstructured":"Varish Mulwad Tim Finin Vijay\u00a0S Kumar Jenny\u00a0Weisenberg Williams Sharad Dixit and Anupam Joshi. 2023. A Practical Entity Linking System for Tables in Scientific Literature. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.10044 (2023)."},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"crossref","unstructured":"Christina Niederer Holger Stitz Reem Hourieh Florian Grassinger Wolfgang Aigner and Marc Streit. 2017. TACO: visualizing changes in tables over time. IEEE Transactions on Visualization and Computer Graphics 24 1 (2017) 677\u2013686.","DOI":"10.1109\/TVCG.2017.2745298"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"crossref","unstructured":"Thorsten Papenbrock Jens Ehrlich Jannik Marten Tommy Neubert Jan-Peer Rudolph Martin Sch\u00f6nberg Jakob Zwiener and Felix Naumann. 2015. Functional dependency discovery: An experimental evaluation of seven algorithms. Proceedings of the VLDB Endowment 8 10 (2015) 1082\u20131093.","DOI":"10.14778\/2794367.2794377"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445063"},{"key":"e_1_3_3_3_35_2","unstructured":"Liang Shi Zhengju Tang Nan Zhang Xiaotong Zhang and Zhi Yang. 2024. A survey on employing large language models for text-to-sql tasks. Comput. Surveys (2024)."},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"crossref","unstructured":"Alexey Shigarov. 2023. Table understanding: Problem overview. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 13 1 (2023) e1482.","DOI":"10.1002\/widm.1482"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"crossref","unstructured":"Sara Steegen Francis Tuerlinckx Andrew Gelman and Wolf Vanpaemel. 2016. Increasing transparency through a multiverse analysis. Perspectives on Psychological Science 11 5 (2016) 702\u2013712.","DOI":"10.1177\/1745691616658637"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"crossref","unstructured":"Min Tian Guozheng Li and Xiaoru Yuan. 2023. LitVis: a visual analytics approach for managing and exploring literature. Journal of Visualization 26 6 (2023) 1445\u20131458.","DOI":"10.1007\/s12650-023-00941-3"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"crossref","unstructured":"Kai Xiong Siwei Fu Guoming Ding Zhongsu Luo Rong Yu Wei Chen Hujun Bao and Yingcai Wu. 2022. Visualizing the scripts of data wrangling with SOMNUS. IEEE Transactions on Visualization and Computer Graphics 29 6 (2022) 2950\u20132964.","DOI":"10.1109\/TVCG.2022.3144975"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714321"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"crossref","unstructured":"Kai Xiong Zhongsu Luo Siwei Fu Yongheng Wang Mingliang Xu and Yingcai Wu. 2022. Revealing the semantics of data wrangling scripts with comantics. IEEE Transactions on Visualization and Computer Graphics 29 1 (2022) 117\u2013127.","DOI":"10.1109\/TVCG.2022.3209470"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14035"},{"key":"e_1_3_3_3_43_2","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et\u00a0al. 2025. Qwen3 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.09388 (2025)."},{"key":"e_1_3_3_3_44_2","unstructured":"Pengcheng Yin Graham Neubig Wen-tau Yih and Sebastian Riedel. 2020. TaBERT: Pretraining for joint understanding of textual and tabular data. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.08314 (2020)."},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3372191"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"crossref","unstructured":"Minzhu Yu Yang Wang Xiaomin Yu Guihua Shan and Zhong Jin. 2023. Pubexplorer: An interactive analytical system for visualizing publication data. Visual Informatics 7 3 (2023) 65\u201374.","DOI":"10.1016\/j.visinf.2023.07.001"},{"key":"e_1_3_3_3_47_2","unstructured":"Dan Zhang Yoshihiko Suhara Jinfeng Li Madelon Hulsebos \u00c7a\u011fatay Demiralp and Wang-Chiew Tan. 2019. Sato: Contextual semantic type detection in tables. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1911.06311 (2019)."},{"key":"e_1_3_3_3_48_2","unstructured":"Haoxiang Zhang Yurong Liu A\u00e9cio Santos Juliana Freire et\u00a0al. 2025. Autoddg: Automated dataset description generation using large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.01050 (2025)."},{"key":"e_1_3_3_3_49_2","unstructured":"Han Zhang Yuheng Ma and Hanfang Yang. 2024. Alter: Augmentation for large-table-based reasoning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.03061 (2024)."},{"key":"e_1_3_3_3_50_2","unstructured":"Victor Zhong Caiming Xiong and Richard Socher. 2017. Seq2sql: Generating structured queries from natural language using reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1709.00103 (2017)."},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714239"}],"event":{"name":"CHI 2026: CHI Conference on Human Factors in Computing Systems","location":"Barcelona Spain","acronym":"CHI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3791449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T07:28:49Z","timestamp":1776065329000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3791449"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":50,"alternative-id":["10.1145\/3772318.3791449","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3791449","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}