{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:58:55Z","timestamp":1750309135814,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T00:00:00Z","timestamp":1726012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Practical Automated Software Bug Fixing via Syntactic and Semantic Analyses","award":["DE220101057"],"award-info":[{"award-number":["DE220101057"]}]},{"name":"Data-Driven Code Reviews for Cost-Effective Software Quality Assurance","award":["DE210101091"],"award-info":[{"award-number":["DE210101091"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,9,11]]},"DOI":"10.1145\/3650212.3680314","type":"proceedings-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T11:44:25Z","timestamp":1726055065000},"page":"704-716","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["VRDSynth: Synthesizing Programs for Multilingual Visually Rich Document Information Extraction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7751-6510","authenticated-orcid":false,"given":"Thanh-Dat","family":"Nguyen","sequence":"first","affiliation":[{"name":"University of Melbourne, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2055-5121","authenticated-orcid":false,"given":"Tung","family":"Do-Viet","sequence":"additional","affiliation":[{"name":"Cinnamon AI, Ho Chi Minh, Vietnam"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5039-4923","authenticated-orcid":false,"given":"Hung","family":"Nguyen-Duy","sequence":"additional","affiliation":[{"name":"Independent Researcher, Hanoi, Vietnam"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7524-951X","authenticated-orcid":false,"given":"Tuan-Hai","family":"Luu","sequence":"additional","affiliation":[{"name":"Cinnamon AI, Ho Chi Minh, Vietnam"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3126-184X","authenticated-orcid":false,"given":"Hung","family":"Le","sequence":"additional","affiliation":[{"name":"Deakin University, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5044-1582","authenticated-orcid":false,"given":"Bach","family":"Le","sequence":"additional","affiliation":[{"name":"University of Melbourne, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6328-8839","authenticated-orcid":false,"given":"Patanamon","family":"Thongtanunam","sequence":"additional","affiliation":[{"name":"University of Melbourne, Melbourne, Australia"}]}],"member":"320","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. https:\/\/github.com\/microsoft\/unilm\/issues\/586 Accessed: 2023-12."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13640-017-0229-7"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"Anonymous Anonymous. 2024. VRDSynth Replication Package. https:\/\/doi.org\/10.5281\/ZENODO.12663279 10.5281\/ZENODO.12663279","DOI":"10.5281\/ZENODO.12663279"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591248"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2009.204"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Syed Saqib Bukhari Faisal Shafait and Thomas M Breuel. 2011. High Performance Layout Analysis of Arabic and Urdu Document Images. Icdar 1275\u20131279. isbn:978-1-4577-1350-7","DOI":"10.1109\/ICDAR.2011.257"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571226"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_9_1","first-page":"812","article-title":"Near Duplicate Image Detection: min-Hash and tf-idf Weighting","volume":"810","author":"Chum Ondrej","year":"2008","unstructured":"Ondrej Chum, James Philbin, and Andrew Zisserman. 2008. Near Duplicate Image Detection: min-Hash and tf-idf Weighting.. In BMVC. 810, 812\u2013815.","journal-title":"BMVC."},{"key":"e_1_3_2_1_10_1","unstructured":"Dr Ciravegna. 2001. Adaptive information extraction from text by rule induction and generalisation."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_12_1","volume-title":"2018 13th IAPR International Workshop on Document Analysis Systems (DAS). 251\u2013256","author":"Andecy Vincent Poulain","year":"2018","unstructured":"Vincent Poulain d\u2019Andecy, Emmanuel Hartmann, and Mar\u00e7al Rusinol. 2018. Field extraction by hybrid incremental and a-priori structural templates. In 2018 13th IAPR International Workshop on Document Analysis Systems (DAS). 251\u2013256."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412778"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2807\u20132816","author":"Ding Yihao","year":"2023","unstructured":"Yihao Ding, Siqu Long, Jiabin Huang, Kaixuan Ren, Xingxiang Luo, Hyunsuk Chung, and Soyeon Caren Han. 2023. Form-NLU: Dataset for the Form Natural Language Understanding. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2807\u20132816."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Yihao Ding Lorenzo Vaiani Caren Han Jean Lee Paolo Garza Josiah Poon and Luca Cagliero. 2024. M3-VRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding. arxiv:cs.CL\/2402.17983. arxiv:2402.17983","DOI":"10.18653\/v1\/2024.findings-acl.903"},{"key":"e_1_3_2_1_16_1","unstructured":"FacebookAI. [n.d.]. XLM-RoBERTa-Base. https:\/\/huggingface.co\/FacebookAI\/xlm-roberta-base Accessed: 2024-03-25."},{"key":"e_1_3_2_1_17_1","unstructured":"FacebookAI. [n.d.]. XLM-RoBERTa-Large. https:\/\/huggingface.co\/FacebookAI\/xlm-roberta-large Accessed: 2024-03-25."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1925844.1926423"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Sumit Gulwani Oleksandr Polozov Rishabh Singh and Boston Delft. 2017. Program Synthesis. isbn:9781680832921","DOI":"10.1561\/9781680832938"},{"key":"e_1_3_2_1_20_1","unstructured":"Will Hamilton Zhitao Ying and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Advances in neural information processing systems. 1024\u20131034."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2000.899505"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1227996"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3322485"},{"key":"e_1_3_2_1_25_1","volume-title":"Hazim Kemal Ekenel, and Jean-Philippe Thiran","author":"Jaume Guillaume","year":"2019","unstructured":"Guillaume Jaume, Hazim Kemal Ekenel, and Jean-Philippe Thiran. 2019. FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents. may, arxiv:1905.13538. arxiv:1905.13538"},{"key":"e_1_3_2_1_26_1","volume-title":"Chargrid: Towards Understanding 2D Documents. isbn:0161-5505 arxiv:1809.08799.","author":"Katti Anoop Raveendra","year":"2018","unstructured":"Anoop Raveendra Katti, Christian Reisswig, Cordula Guder, Sebastian Brarda, Steffen Bickel, Johannes H\u00f6hne, and Jean Baptiste Faddoul. 2018. Chargrid: Towards Understanding 2D Documents. isbn:0161-5505 arxiv:1809.08799."},{"key":"e_1_3_2_1_27_1","unstructured":"Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907."},{"key":"e_1_3_2_1_28_1","unstructured":"Xiaojing Liu Feiyu Gao Qiong Zhang and Huasha Zhao. 2019. Graph Convolution for Multimodal Information Extraction from Visually Rich Documents. arxiv:1903.11279. arxiv:1903.11279"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","unstructured":"D. Lohani A. Bela\u00efd and Y. Bela\u00efd. 2019. An Invoice Reading System Using a Graph Convolutional Network. 144\u2013158. https:\/\/doi.org\/10.1007\/978-3-030-21074-8_12 10.1007\/978-3-030-21074-8_12","DOI":"10.1007\/978-3-030-21074-8_12"},{"key":"e_1_3_2_1_30_1","unstructured":"Microsoft. [n.d.]. InfoXLM-Base. https:\/\/huggingface.co\/microsoft\/infoxlm-base Accessed: 2024-03-25."},{"key":"e_1_3_2_1_31_1","unstructured":"Microsoft. [n.d.]. InfoXLM-Large. https:\/\/huggingface.co\/microsoft\/infoxlm-large Accessed: 2024-03-25."},{"key":"e_1_3_2_1_32_1","unstructured":"Microsoft. [n.d.]. LayoutXLM-Base. https:\/\/huggingface.co\/microsoft\/layoutxlm-base Accessed: 2024-03-25."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510455.3512780"},{"key":"e_1_3_2_1_34_1","unstructured":"Maxwell Nye Luke Hewitt Joshua Tenenbaum and Armando Solar-Lezama. 2019. Learning to Infer Program Sketches. feb arxiv:1902.06349. arxiv:1902.06349"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.74"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3519939.3523705"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Haoyuan Peng Lu Liu Yi Zhou Junying Zhou and Xiaoqing Zheng. 2018. Attention-based Belief or Disbelief Feature Extraction for Dependency Parsing. AAAI.","DOI":"10.1609\/aaai.v32i1.12005"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Shah Rukh Qasim Hassan Mahmood and Faisal Shafait. 2019. Rethinking Table Parsing using Graph Neural Networks. may arxiv:1905.13391.","DOI":"10.1109\/ICDAR.2019.00031"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Shah Rukh Qasim Hassan Mahmood and Faisal Shafait. 2019. Rethinking Table Recognition using Graph Neural Networks. may arxiv:1905.13391. arxiv:1905.13391","DOI":"10.1109\/ICDAR.2019.00031"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380608"},{"key":"e_1_3_2_1_41_1","unstructured":"Niels Rogge. 2023. Fine-tune LayoutXLM on XFUND (relation extraction). https:\/\/github.com\/NielsRogge\/Transformers-Tutorials\/blob\/master\/LayoutXLM\/Fine_tune_LayoutXLM_on_XFUND_(relation_extraction).ipynb Accessed: 2023-12."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.223"},{"volume-title":"Program Synthesis with Equivalence Reduction","author":"Smith Calvin","key":"e_1_3_2_1_43_1","unstructured":"Calvin Smith and Aws Albarghouthi. 2019. Program Synthesis with Equivalence Reduction. In Verification, Model Checking, and Abstract Interpretation, Constantin Enea and Ruzica Piskac (Eds.). Springer International Publishing, Cham. 24\u201347. isbn:978-3-030-11245-5"},{"key":"e_1_3_2_1_44_1","unstructured":"Brandon Smock and Rohith Pesala. 2021. Table Transformer. https:\/\/github.com\/microsoft\/table-transformer"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Linfeng Song Yue Zhang Zhiguo Wang and Daniel Gildea. 2018. N-ary relation extraction using graph state lstm. arXiv preprint arXiv:1808.09101.","DOI":"10.18653\/v1\/D18-1246"},{"key":"e_1_3_2_1_47_1","unstructured":"Vishal Sunder Ashwin Srinivasan Lovekesh Vig Gautam Shroff and Rohit Rahul. 2019. One-shot Information Extraction from Document Images using Neuro-Deductive Program Synthesis. jun arxiv:1906.02427. arxiv:1906.02427"},{"key":"e_1_3_2_1_48_1","volume-title":"British Machine Vision Conference (BMVC), 1\u201312","author":"Tuan Anh Nguyen Dang","year":"2019","unstructured":"Nguyen Dang Tuan Anh and Nguyen Thanh Dat. 2019. End-to-End Information Extraction by Character-Level Embedding and Multi-Stage. British Machine Vision Conference (BMVC), 1\u201312."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"Wenlin Wang Zhe Gan Hongteng Xu Ruiyi Zhang Guoyin Wang Dinghan Shen Changyou Chen and Lawrence Carin. 2019. Topic-Guided Variational Autoencoders for Text Generation. mar arxiv:1903.07137. arxiv:1903.07137","DOI":"10.18653\/v1\/N19-1015"},{"key":"e_1_3_2_1_50_1","unstructured":"Yiheng Xu Minghao Li Lei Cui Shaohan Huang Furu Wei and Ming Zhou. 2019. LayoutLM: Pre-training of Text and Layout for Document Image Understanding. arxiv:cs.CL\/1912.13318."},{"key":"e_1_3_2_1_51_1","unstructured":"Yiheng Xu Tengchao Lv Lei Cui Guoxin Wang Yijuan Lu Dinei Florencio Cha Zhang and Furu Wei. 2021. LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding. arxiv:cs.CL\/2104.08836."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2002.1184038"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1078"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"crossref","unstructured":"Chong Zhang Ya Guo Yi Tu Huan Chen Jinyang Tang Huijia Zhu Qi Zhang and Tao Gui. 2023. Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction. arXiv preprint arXiv:2310.11016.","DOI":"10.18653\/v1\/2023.emnlp-main.846"}],"event":{"name":"ISSTA '24: 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","AITO"],"location":"Vienna Austria","acronym":"ISSTA '24"},"container-title":["Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650212.3680314","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3650212.3680314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:07Z","timestamp":1750287007000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650212.3680314"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,11]]},"references-count":55,"alternative-id":["10.1145\/3650212.3680314","10.1145\/3650212"],"URL":"https:\/\/doi.org\/10.1145\/3650212.3680314","relation":{},"subject":[],"published":{"date-parts":[[2024,9,11]]},"assertion":[{"value":"2024-09-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}