{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T15:20:50Z","timestamp":1774452050585,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"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":[[2024,10,21]]},"DOI":"10.1145\/3627673.3680000","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:21Z","timestamp":1729452861000},"page":"4056-4060","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["<i>\n              <scp>Tabularis Revilio:<\/scp>\n            <\/i>\n            Converting Text to Tables"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9510-4512","authenticated-orcid":false,"given":"Mukul","family":"Singh","sequence":"first","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9182-597X","authenticated-orcid":false,"given":"Gust","family":"Verbruggen","sequence":"additional","affiliation":[{"name":"Microsoft, Keerbergen, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3727-3291","authenticated-orcid":false,"given":"Vu","family":"Le","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9226-9634","authenticated-orcid":false,"given":"Sumit","family":"Gulwani","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3115\/1572364.1572390"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2501511.2501516"},{"key":"e_1_3_2_1_3_1","volume-title":"PDF Table Extraction for Humans. https:\/\/github.com\/camelot-dev\/camelot. [Online","year":"2024","unstructured":"Camelot. 2023. PDF Table Extraction for Humans. https:\/\/github.com\/camelot-dev\/camelot. [Online; accessed May-2024]."},{"key":"e_1_3_2_1_4_1","volume-title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks. Transactions on Machine Learning Research","author":"Chen Wenhu","year":"2023","unstructured":"Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W Cohen. 2023. Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks. Transactions on Machine Learning Research (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Complicated Table Structure Recognition. arxiv","author":"Chi Zewen","year":"1908","unstructured":"Zewen Chi, Heyan Huang, Heng-Da Xu, Houjin Yu, Wanxuan Yin, and Xian-Ling Mao. 2019. Complicated Table Structure Recognition. arxiv: 1908.04729 [cs.IR]"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.250"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242583"},{"key":"e_1_3_2_1_8_1","volume-title":"Allie Del Giorno, Sivakanth Gopi, Mojan Javaheripi, Piero Kauffmann, Gustavo de Rosa, Olli Saarikivi, et al.","author":"Gunasekar Suriya","year":"2023","unstructured":"Suriya Gunasekar, Yi Zhang, Jyoti Aneja, Caio C\u00e9sar Teodoro Mendes, Allie Del Giorno, Sivakanth Gopi, Mojan Javaheripi, Piero Kauffmann, Gustavo de Rosa, Olli Saarikivi, et al. 2023. Textbooks are all you need. arXiv preprint arXiv:2306.11644 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"INFOTABS: Inference on Tables as Semi-structured Data. arxiv","author":"Gupta Vivek","year":"2020","unstructured":"Vivek Gupta, Maitrey Mehta, Pegah Nokhiz, and Vivek Srikumar. 2020. INFOTABS: Inference on Tables as Semi-structured Data. arxiv: 2005.06117 [cs.CL]"},{"key":"e_1_3_2_1_10_1","volume-title":"Multi-Cell Decoder and Mutual Learning for Table Structure and Character Recognition. arXiv preprint arXiv:2404.13268","author":"Kawakatsu Takaya","year":"2024","unstructured":"Takaya Kawakatsu. 2024. Multi-Cell Decoder and Mutual Learning for Table Structure and Character Recognition. arXiv preprint arXiv:2404.13268 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"The T-Recs Table Recognition and Analysis System. In International Workshop on Document Analysis Systems. https:\/\/api.semanticscholar.org\/CorpusID:38477730","author":"Kieninger Thomas","unstructured":"Thomas Kieninger and Andreas R. Dengel. 1998. The T-Recs Table Recognition and Analysis System. In International Workshop on Document Analysis Systems. https:\/\/api.semanticscholar.org\/CorpusID:38477730"},{"key":"e_1_3_2_1_12_1","unstructured":"Raymond Li Yangtian Zi Niklas Muennighoff Denis Kocetkov Chenghao Mou Marc Marone Christopher Akiki LI Jia Jenny Chim Qian Liu et al. 2023. StarCoder: may the source be with you! Transactions on Machine Learning Research (2023)."},{"key":"e_1_3_2_1_13_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li and Yong Jae Lee. 2023. Improved Baselines with Visual Instruction Tuning."},{"key":"e_1_3_2_1_14_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning. In NeurIPS."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3276520"},{"key":"e_1_3_2_1_17_1","volume-title":"TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images. arxiv","author":"Paliwal Shubham","year":"2001","unstructured":"Shubham Paliwal, Vishwanath D, Rohit Rahul, Monika Sharma, and Lovekesh Vig. 2020. TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images. arxiv: 2001.01469 [cs.CV]"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/897352"},{"key":"e_1_3_2_1_19_1","volume-title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arxiv","author":"Reimers Nils","year":"1908","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arxiv: 1908.10084 [cs.CL]"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.40097"},{"key":"e_1_3_2_1_21_1","unstructured":"Baptiste Rozi\u00e8re Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing Ellen Tan Yossi Adi Jingyu Liu Romain Sauvestre Tal Remez J\u00e9r\u00e9my Rapin Artyom Kozhevnikov Ivan Evtimov Joanna Bitton Manish Bhatt Cristian Canton Ferrer Aaron Grattafiori Wenhan Xiong Alexandre D\u00e9fossez Jade Copet Faisal Azhar Hugo Touvron Louis Martin Nicolas Usunier Thomas Scialom and Gabriel Synnaeve. 2024. Code Llama: Open Foundation Models for Code. arxiv: 2308.12950 [cs.CL]"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.192"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-014-0226-7"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Brandon Smock Rohith Pesala and Robin Abraham. 2021. PubTables-1M: Towards comprehensive table extraction from unstructured documents. arxiv: 2110.00061 [cs.LG]","DOI":"10.1109\/CVPR52688.2022.00459"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-019-00646-y"},{"key":"e_1_3_2_1_26_1","volume-title":"Deep High-Resolution Representation Learning for Visual Recognition. arxiv","author":"Wang Jingdong","year":"1908","unstructured":"Jingdong Wang, Ke Sun, Tianheng Cheng, Borui Jiang, Chaorui Deng, Yang Zhao, Dong Liu, Yadong Mu, Mingkui Tan, Xinggang Wang, Wenyu Liu, and Bin Xiao. 2020. Deep High-Resolution Representation Learning for Visual Recognition. arxiv: 1908.07919 [cs.CV]"},{"key":"e_1_3_2_1_27_1","volume-title":"Nghi D. Q. Bui, Junnan Li, and Steven C. H. Hoi.","author":"Wang Yue","year":"2023","unstructured":"Yue Wang, Hung Le, Akhilesh Deepak Gotmare, Nghi D. Q. Bui, Junnan Li, and Steven C. H. Hoi. 2023. CodeT5: Open Code Large Language Models for Code Understanding and Generation. arxiv: 2305.07922 [cs.CL]"},{"key":"e_1_3_2_1_28_1","unstructured":"Xueqing Wu Jiacheng Zhang and Hang Li. 2022. Text-to-Table: A New Way of Information Extraction. arxiv: 2109.02707 [cs.CL]"},{"key":"e_1_3_2_1_29_1","unstructured":"Zilong Zhao Robert Birke and Lydia Chen. 2023. TabuLa: Harnessing Language Models for Tabular Data Synthesis. arxiv: 2310.12746 [cs.LG]"},{"key":"e_1_3_2_1_30_1","volume-title":"Image-based table recognition: data, model, and evaluation. arXiv preprint arXiv:1911.10683","author":"Zhong Xu","year":"2019","unstructured":"Xu Zhong, Elaheh ShafieiBavani, and Antonio Jimeno Yepes. 2019. Image-based table recognition: data, model, and evaluation. arXiv preprint arXiv:1911.10683 (2019)."}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3680000","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3680000","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:17Z","timestamp":1750294697000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3680000"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":29,"alternative-id":["10.1145\/3627673.3680000","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3680000","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}