{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:21:22Z","timestamp":1750220482004,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T00:00:00Z","timestamp":1635206400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076231, U1811461"],"award-info":[{"award-number":["62076231, U1811461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2017YFB1002104"],"award-info":[{"award-number":["2017YFB1002104"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,26]]},"DOI":"10.1145\/3459637.3481929","type":"proceedings-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T15:53:43Z","timestamp":1636991623000},"page":"4264-4272","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Jura"],"prefix":"10.1145","author":[{"given":"Zhengqi","family":"Xu","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixuan","family":"Cao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongyu","family":"Cao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoxiang","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Paoding Technology Co., LTD., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuanqiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Paoding Technology Co., LTD., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Pang","sequence":"additional","affiliation":[{"name":"Beijing Paoding Technology Co., LTD., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangbin","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Paoding Technology Co., LTD., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Paoding Technology Co., LTD., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Allie","family":"Cheung","sequence":"additional","affiliation":[{"name":"Hong Kong Exchanges and Clearing Limited, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Tam","sequence":"additional","affiliation":[{"name":"Hong Kong Exchanges and Clearing Limited, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lukas","family":"Petrikas","sequence":"additional","affiliation":[{"name":"Hong Kong Exchanges and Clearing Limited, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Luo","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,30]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Najah-imane Bentabet. 2019. Table-Of-Contents generation on contemporary documents. In ICDAR.  Najah-imane Bentabet. 2019. Table-Of-Contents generation on contemporary documents. In ICDAR.","DOI":"10.1109\/ICDAR.2019.00025"},{"volume-title":"Extracting Variable-Depth Logical Document Hierarchy from Long Documents: Method, Evaluation, and Application. Journal of Computer Sciecne and Technology","year":"2021","author":"Cao Rongyu","key":"e_1_3_2_2_3_1"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186166"},{"key":"e_1_3_2_2_5_1","unstructured":"Alan Conway. 1993. Page grammars and page parsing: A syntactic approach to documentlayout recognition. In ICDAR.  Alan Conway. 1993. Page grammars and page parsing: A syntactic approach to documentlayout recognition. In ICDAR."},{"volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL.","year":"2019","author":"Devlin Jacob","key":"e_1_3_2_2_6_1"},{"key":"e_1_3_2_2_7_1","unstructured":"Thorsten Joachims. 1997. A Probabilistic Analysis of the Rocchio Algorithm with TFIDF for Text Categorization.  Thorsten Joachims. 1997. A Probabilistic Analysis of the Rocchio Algorithm with TFIDF for Text Categorization."},{"volume-title":"The 8 most popular document formats on the web. Duff Johnson Strategy and Communications Blog","year":"2014","author":"Johnson Duff","key":"e_1_3_2_2_8_1"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Yoon Kim. 2014. Convolutional neural networks for sentence classification. (2014).  Yoon Kim. 2014. Convolutional neural networks for sentence classification. (2014).","DOI":"10.3115\/v1\/D14-1181"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10506-017-9206-9"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIME.2009.101"},{"key":"e_1_3_2_2_12_1","unstructured":"Hongwei Li Qingping Yang Yixuan Cao Jiaquan Yao and Ping Luo. 2020 c. Cracking Tabular Presentation Diversity for Automatic Cross-Checking over Numerical Facts. In KDD.  Hongwei Li Qingping Yang Yixuan Cao Jiaquan Yao and Ping Luo. 2020 c. Cracking Tabular Presentation Diversity for Automatic Cross-Checking over Numerical Facts. In KDD."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Kai Li Curtis Wigington Chris Tensmeyer Handong Zhao Nikolaos Barmpalios Vlad I. Morariu Varun Manjunatha Tong Sun and Yun Fu. 2020 a. Cross-Domain Document Object Detection: Benchmark Suite and Method. In CVPR.  Kai Li Curtis Wigington Chris Tensmeyer Handong Zhao Nikolaos Barmpalios Vlad I. Morariu Varun Manjunatha Tong Sun and Yun Fu. 2020 a. Cross-Domain Document Object Detection: Benchmark Suite and Method. In CVPR.","DOI":"10.1109\/CVPR42600.2020.01293"},{"volume-title":"TableBank: Table Benchmark for Image-based Table Detection and Recognition. International Conference on Document Analysis and Recognition (ICDAR).","year":"2019","author":"Li Minghao","key":"e_1_3_2_2_14_1"},{"volume-title":"2020 b. DocBank: A Benchmark Dataset for Document Layout Analysis. ArXiv","year":"2020","author":"Li Minghao","key":"e_1_3_2_2_15_1"},{"key":"e_1_3_2_2_16_1","unstructured":"Tie-Yan Liu. 2009. Learning to Rank for Information Retrieval. Found. Trends Inf. Retr. (2009).  Tie-Yan Liu. 2009. Learning to Rank for Information Retrieval. Found. Trends Inf. Retr. (2009)."},{"volume-title":"Machine learning for reading order detection in document image understanding. Studies in Computational Intelligence","year":"2008","author":"Malerba Donato","key":"e_1_3_2_2_17_1"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824058"},{"volume-title":"Document Structure Analysis Algorithms: a Literature Survey. Document Recognition and Retrieval","year":"2003","author":"Mao Song","key":"e_1_3_2_2_19_1"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Jean Luc Meunier. 2005. Optimized XY-cut for determining a page reading order. In ICDAR.  Jean Luc Meunier. 2005. Optimized XY-cut for determining a page reading order. In ICDAR.","DOI":"10.1109\/ICDAR.2005.182"},{"volume-title":"Macro F1 and Macro F1. ArXiv","year":"2019","author":"Opitz Juri","key":"e_1_3_2_2_21_1"},{"key":"e_1_3_2_2_22_1","unstructured":"F. Canan Pembe and Tunga G\u00fc ng\u00f6 r. 2010. A Tree Learning Approach to Web Document Sectional Hierarchy Extraction. In ICAART.  F. Canan Pembe and Tunga G\u00fc ng\u00f6 r. 2010. A Tree Learning Approach to Web Document Sectional Hierarchy Extraction. In ICAART."},{"volume-title":"Understanding the Logical and Semantic Structure of Large Documents. CoRR","year":"2017","author":"Rahman Muhammad Mahbubur","key":"e_1_3_2_2_23_1"},{"volume-title":"Relevance weighting of search terms. Journal of the American Society for Information science","year":"1976","author":"Robertson Stephen E","key":"e_1_3_2_2_24_1"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/361219.361220"},{"volume":"202","journal-title":"Christopher J. Butler.","author":"Sherchan Wanita","key":"e_1_3_2_2_26_1"},{"volume-title":"Thompson","year":"1986","author":"Spector Alfred Z","key":"e_1_3_2_2_27_1"},{"key":"e_1_3_2_2_28_1","unstructured":"Raymond E Wright. 1995. Logistic regression. (1995).  Raymond E Wright. 1995. Logistic regression. (1995)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"Yang Xiao Ersin Yumer Paul Asente Mike Kraley Daniel Kifer and C. Lee Giles. 2017. Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network. In CVPR.  Yang Xiao Ersin Yumer Paul Asente Mike Kraley Daniel Kifer and C. Lee Giles. 2017. Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network. In CVPR.","DOI":"10.1109\/CVPR.2017.462"},{"volume-title":"Semantic NLP-based information extraction from construction regulatory documents for automated compliance checking. Journal of Computing in Civil Engineering","year":"2016","author":"Zhang Jiansong","key":"e_1_3_2_2_30_1"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00166"}],"event":{"name":"CIKM '21: The 30th ACM International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Virtual Event Queensland Australia","acronym":"CIKM '21"},"container-title":["Proceedings of the 30th ACM International Conference on Information & Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3481929","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3459637.3481929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:58Z","timestamp":1750193338000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3481929"}},"subtitle":["Towards Automatic Compliance Assessment for Annual Reports of Listed Companies"],"short-title":[],"issued":{"date-parts":[[2021,10,26]]},"references-count":30,"alternative-id":["10.1145\/3459637.3481929","10.1145\/3459637"],"URL":"https:\/\/doi.org\/10.1145\/3459637.3481929","relation":{},"subject":[],"published":{"date-parts":[[2021,10,26]]},"assertion":[{"value":"2021-10-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}