{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T02:45:12Z","timestamp":1775097912853,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,27]]},"DOI":"10.1145\/3704268.3742697","type":"proceedings-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:44:47Z","timestamp":1756313087000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Document Classification using File Names"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9531-1251","authenticated-orcid":false,"given":"Zhijian","family":"Li","sequence":"first","affiliation":[{"name":"Vanderbilt University, Nashville, Tennessee, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4907-7888","authenticated-orcid":false,"given":"Stefan","family":"Larson","sequence":"additional","affiliation":[{"name":"Vanderbilt University, Nashville, Tennessee, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4001-3442","authenticated-orcid":false,"given":"Kevin","family":"Leach","sequence":"additional","affiliation":[{"name":"Vanderbilt University, Nashville, Tennessee, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Short text classification approach to identify child sexual exploitation material. Scientific Reports 13, 1","author":"Wesam Al-Nabki MHD","year":"2023","unstructured":"MHD Wesam Al-Nabki, Eduardo Fidalgo, Enrique Alegre, and Rocio Alaiz-Rodriguez. 2023. Short text classification approach to identify child sexual exploitation material. Scientific Reports 13, 1 (2023). https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC10522674\/pdf\/41598_2023_Article_42902.pdf"},{"key":"e_1_3_2_1_2_1","volume-title":"Yusheng Xie, and R. Manmatha.","author":"Appalaraju Srikar","year":"2021","unstructured":"Srikar Appalaraju, Bhavan Jasani, Bhargava Urala Kota, Yusheng Xie, and R. Manmatha. 2021. DocFormer: End-to-End Transformer for Document Understanding. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). https:\/\/openaccess.thecvf.com\/content\/ICCV2021\/papers\/Appalaraju_DocFormer_End-to-End_Transformer_for_Document_Understanding_ICCV_2021_paper.pdf"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3115\/1219044.1219075"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1079"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the Eighth International Conference on Probabilistic Graphical Models. 136--146","author":"Dementiev Eugene","year":"2016","unstructured":"Eugene Dementiev and Norman Fenton. 2016. Bayesian Torrent Classification by File Name and Size Only. In Proceedings of the Eighth International Conference on Probabilistic Graphical Models. 136--146. http:\/\/proceedings.mlr.press\/v52\/dementiev16.pdf"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). https:\/\/aclanthology.org\/N19-1423","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). https:\/\/aclanthology.org\/N19-1423"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2930339"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024","author":"Fujitake Masato","year":"2024","unstructured":"Masato Fujitake. 2024. LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). https:\/\/aclanthology.org\/2024.lrec-main.892"},{"key":"e_1_3_2_1_10_1","volume-title":"Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval. In International Conference on Document Analysis and Recognition (ICDAR). https: \/\/arxiv.org\/pdf\/1502","author":"Harley Adam W.","unstructured":"Adam W. Harley, Alex Ufkes, and Konstantinos G. Derpanis. 2015. Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval. In International Conference on Document Analysis and Recognition (ICDAR). https: \/\/arxiv.org\/pdf\/1502.07058"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of International Conference on Learning Representations (ICLR). https:\/\/arxiv.org\/pdf\/1610","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Abaseline for detecting misclassified and out-of-distribution examples in neural networks. In Proceedings of International Conference on Learning Representations (ICLR). https:\/\/arxiv.org\/pdf\/1610.02136.pdf"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469096.3475060"},{"key":"e_1_3_2_1_14_1","volume-title":"Faker: A Python Package for Generating Fake Data. https:\/\/pypi.org\/project\/Faker\/0.7.4\/","year":"2016","unstructured":"joke2k. 2016. Faker: A Python Package for Generating Fake Data. https:\/\/pypi.org\/project\/Faker\/0.7.4\/"},{"key":"e_1_3_2_1_15_1","volume-title":"Large scale subject category classification of scholarly papers with Deep Attentive Neural Networks. Frontiers in research metrics and analytics 5","author":"Kandimalla Bharath","year":"2021","unstructured":"Bharath Kandimalla, Shaurya Rohatgi, Jian Wu, and C. Lee Giles. 2021. Large scale subject category classification of scholarly papers with Deep Attentive Neural Networks. Frontiers in research metrics and analytics 5 (2021), 600382. https:\/\/pmc.ncbi.nlm.nih.gov\/articles\/PMC8025978\/pdf\/frma-05-600382.pdf"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.248"},{"key":"e_1_3_2_1_18_1","unstructured":"Stefan Larson Gordon Lim Yutong Ai David Kuang and Kevin Leach. 2022. Evaluating Out-of-Distribution Performance on Document Image Classifiers. In Proceedings of the 36th Conference on Neural Information Processing Systems Track on Datasets and Benchmarks. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/4c0986bd04d747745beba3752bdf4d9d-Paper-Datasets_and_Benchmarks.pdf"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Stefan Larson Anish Mahendran Joseph J. Peper Christopher Clarke Andrew Lee Parker Hill Jonathan K. Kummerfeld Kevin Leach Michael A. Laurenzano Lingjia Tang and Jason Mars. 2019. An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). https:\/\/aclanthology.org\/D19-1131","DOI":"10.18653\/v1\/D19-1131"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547911"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006132"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.79"},{"key":"e_1_3_2_1_23_1","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","author":"Pedregosa Fabian","year":"2011","unstructured":"Fabian Pedregosa, Ga\u00ebl Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, et al. 2011. Scikit-learn: Machine learning in Python. Journal of machine learning research 12, Oct (2011), 2825--2830. https:\/\/www.jmlr.org\/papers\/volume12\/pedregosa11a\/pedregosa11a.pdf","journal-title":"Journal of machine learning research 12"},{"key":"e_1_3_2_1_24_1","volume-title":"Understanding Long Documents with Different Position-Aware Attentions. arXiv preprint arXiv.2208.08201","author":"Pham Hai","year":"2022","unstructured":"Hai Pham, Guoxin Wang, Yijuan Lu, Dinei Florencio, and Cha Zhang. 2022. Understanding Long Documents with Different Position-Aware Attentions. arXiv preprint arXiv.2208.08201 (2022). https:\/\/arxiv.org\/abs\/2208.08201"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3168681"},{"key":"e_1_3_2_1_26_1","volume-title":"Best of Both Worlds: A Pliable and Generalizable Neuro-Symbolic Approach for Relation Classification. In Findings of the Association for Computational Linguistics: NAACL 2024","author":"Vacareanu Robert","year":"2024","unstructured":"Robert Vacareanu, Fahmida Alam, Md Asiful Islam, Haris Riaz, and Mihai Surdeanu. 2024. Best of Both Worlds: A Pliable and Generalizable Neuro-Symbolic Approach for Relation Classification. In Findings of the Association for Computational Linguistics: NAACL 2024. https:\/\/aclanthology.org\/2024.findings-naacl.165\/"},{"key":"e_1_3_2_1_27_1","volume-title":"Rule-based information extraction: Advantages, limitations, and perspectives. Jusletter IT (02 2018) 4","author":"Waltl Bernhard","year":"2018","unstructured":"Bernhard Waltl, Georg Bonczek, and Florian Matthes. 2018. Rule-based information extraction: Advantages, limitations, and perspectives. Jusletter IT (02 2018) 4 (2018)."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. https:\/\/www.aclweb.org\/anthology\/2020","author":"Wolf Thomas","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush. 2020. Transformers: State-of-the-Art Natural Language Processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.201"}],"event":{"name":"DocEng '25: ACM Symposium on Document Engineering 2025","location":"Nottingham United Kingdom","acronym":"DocEng '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 2025 ACM Symposium on Document Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3704268.3742697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T18:26:35Z","timestamp":1760466395000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3704268.3742697"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":30,"alternative-id":["10.1145\/3704268.3742697","10.1145\/3704268"],"URL":"https:\/\/doi.org\/10.1145\/3704268.3742697","relation":{},"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"2025-08-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}