{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:13:00Z","timestamp":1766268780916,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T00:00:00Z","timestamp":1695168000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ANR","award":["21-CE38-0014"],"award-info":[{"award-number":["21-CE38-0014"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,9,20]]},"DOI":"10.1145\/3617233.3617239","type":"proceedings-article","created":{"date-parts":[[2023,12,30]],"date-time":"2023-12-30T06:05:32Z","timestamp":1703916332000},"page":"71-78","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Noisy and Unbalanced Multimodal Document Classification: Textbook Exercises as a Use Case"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1104-1785","authenticated-orcid":false,"given":"Elise","family":"Lincker","sequence":"first","affiliation":[{"name":"Cedric, CNAM, FR"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7249-8715","authenticated-orcid":false,"given":"Camille","family":"Guinaudeau","sequence":"additional","affiliation":[{"name":"JFLI, NII, CNRS, JP and Universit\u00e9 Paris-Saclay, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6423-8630","authenticated-orcid":false,"given":"Olivier","family":"Pons","sequence":"additional","affiliation":[{"name":"Cedric, CNAM, FR"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6171-8989","authenticated-orcid":false,"given":"J\u00e9r\u00f4me","family":"Dupire","sequence":"additional","affiliation":[{"name":"Cedric, CNAM, FR"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3849-4133","authenticated-orcid":false,"given":"C\u00e9line","family":"Hudelot","sequence":"additional","affiliation":[{"name":"MICS, CentraleSup\u00e9lec, FR"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8574-3337","authenticated-orcid":false,"given":"Vincent","family":"Mousseau","sequence":"additional","affiliation":[{"name":"MICS, CentraleSup\u00e9lec, FR"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4299-5061","authenticated-orcid":false,"given":"Isabelle","family":"Barbet","sequence":"additional","affiliation":[{"name":"Cedric, CNAM, FR"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3890-6110","authenticated-orcid":false,"given":"Caroline","family":"Huron","sequence":"additional","affiliation":[{"name":"SEED, INSERM, Universit\u00e9 Paris Cit\u00e9, FR and Learning Planet Institute, France"}]}],"member":"320","published-online":{"date-parts":[[2023,12,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics.","author":"Billami B.","year":"2018","unstructured":"Mokhtar\u00a0B. Billami, Thomas Fran\u00e7ois, and N\u00faria Gala. 2018. ReSyf: a French lexicon with ranked synonyms. In Proceedings of the 27th International Conference on Computational Linguistics."},{"key":"e_1_3_2_1_3_1","volume-title":"Generation of Multiple-Choice Questions from Textbook Contents of School-Level Subjects","author":"Ch Dhawaleswar\u00a0Rao","year":"2022","unstructured":"Dhawaleswar\u00a0Rao Ch and Sujan\u00a0Kumar Saha. 2022. Generation of Multiple-Choice Questions from Textbook Contents of School-Level Subjects. IEEE Transactions on Learning Technologies (2022)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Gabrielle Chenais C\u00e9dric Gil-Jardin\u00e9 H\u00e9l\u00e8ne Touchais Eric Tellier Xavier Combes Loick Bourdois Philippe Revel and Emmanuel Lagarde. 2022. Development and Validation of Deep Learning Transformer Models for Building a Comprehensive and Real-time Trauma Observatory. In preprint.","DOI":"10.2196\/preprints.40843"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.","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."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 12th Language Resources and Evaluation for Language Technologies.","author":"Gala N\u00faria","year":"2020","unstructured":"N\u00faria Gala, Ana\u00efs Tack, Ludivine Javourey-Drevet, Thomas Fran\u00e7ois, and Johannes\u00a0C. Ziegler. 2020. Alector: A Parallel Corpus of Simplified French Texts with Alignments of Misreadings by Poor and Dyslexic Readers. In Proceedings of the 12th Language Resources and Evaluation for Language Technologies."},{"key":"e_1_3_2_1_7_1","volume-title":"Remediating textbook deficiencies by leveraging community question answers. Education and Information Technologies","author":"Ghosh Krishnendu","year":"2022","unstructured":"Krishnendu Ghosh. 2022. Remediating textbook deficiencies by leveraging community question answers. Education and Information Technologies (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems 27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_9_1","volume-title":"A multilevel description of textbook linguistic complexity across disciplines: Leveraging NLP to support disciplinary literacy. Linguistics and Education","author":"Green Clarence","year":"2019","unstructured":"Clarence Green. 2019. A multilevel description of textbook linguistic complexity across disciplines: Leveraging NLP to support disciplinary literacy. Linguistics and Education (2019)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00104"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054689"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the Conference on Computational Humanities Research.","author":"Jiang Ming","year":"2021","unstructured":"Ming Jiang, Yuerong Hu, Glen Worthey, Ryan\u00a0C Dubnicek, Ted Underwood, and J\u00a0Stephen Downie. 2021. Impact of OCR Quality on BERT Embeddings in the Domain Classification of Book Excerpts. In Proceedings of the Conference on Computational Humanities Research."},{"key":"e_1_3_2_1_19_1","volume-title":"A three-level classification of French tweets in ecological crises. Information Processing & Management","author":"Kozlowski Diego","year":"2020","unstructured":"Diego Kozlowski, Elisa Lannelongue, Fr\u00e9d\u00e9ric Saudemont, Farah Benamara, Alda Mari, V\u00e9ronique Moriceau, and Abdelmoumene Boumadane. 2020. A three-level classification of French tweets in ecological crises. Information Processing & Management (2020)."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 12th Language Resources and Evaluation Conference.","author":"Le Hang","year":"2020","unstructured":"Hang Le, Lo\u00efc Vial, Jibril Frej, Vincent Segonne, Maximin Coavoux, Benjamin Lecouteux, Alexandre Allauzen, Benoit Crabb\u00e9, Laurent Besacier, and Didier Schwab. 2020. FlauBERT: Unsupervised Language Model Pre-training for French. In Proceedings of the 12th Language Resources and Evaluation Conference."},{"key":"e_1_3_2_1_21_1","volume-title":"MANULEX: A grade-level lexical database from French elementary school readers. Behavior Research Methods, Instruments, & Computers","author":"L\u00e9t\u00e9 Bernard","year":"2004","unstructured":"Bernard L\u00e9t\u00e9, Liliane Sprenger-Charolles, and Pascale Col\u00e9. 2004. MANULEX: A grade-level lexical database from French elementary school readers. Behavior Research Methods, Instruments, & Computers (2004)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148307"},{"key":"e_1_3_2_1_23_1","volume-title":"LayoutGAN: Generating graphic layouts with wireframe discriminators. arXiv preprint arXiv:1901.06767","author":"Li Jianan","year":"2019","unstructured":"Jianan Li, Jimei Yang, Aaron Hertzmann, Jianming Zhang, and Tingfa Xu. 2019. LayoutGAN: Generating graphic layouts with wireframe discriminators. arXiv preprint arXiv:1901.06767 (2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_25_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_26_1","volume-title":"Content analysis of textbooks via natural language processing: Findings on gender, race, and ethnicity in Texas US history textbooks. AERA Open","author":"Lucy Li","year":"2020","unstructured":"Li Lucy, Dorottya Demszky, Patricia Bromley, and Dan Jurafsky. 2020. Content analysis of textbooks via natural language processing: Findings on gender, race, and ethnicity in Texas US history textbooks. AERA Open (2020)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.645"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the Workshop on Document Intelligence at NeurIPS.","author":"Park Seunghyun","year":"2019","unstructured":"Seunghyun Park, Seung Shin, Bado Lee, Junyeop Lee, Jaeheung Surh, Minjoon Seo, and Hwalsuk Lee. 2019. CORD: a consolidated receipt dataset for post-OCR parsing. In Proceedings of the Workshop on Document Intelligence at NeurIPS."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86331-9_47"},{"key":"e_1_3_2_1_31_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever and others. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_32_1","volume":"202","author":"Raffel Colin","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter\u00a0J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research (2020).","journal-title":"J Liu."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 7th Workshop on the Challenges in the Management of Large Corpora.","author":"Javier\u00a0Ortiz Su\u00e1rez Pedro","year":"2019","unstructured":"Pedro Javier\u00a0Ortiz Su\u00e1rez, Beno\u00eet Sagot, and Laurent Romary. 2019. Asynchronous pipeline for processing huge corpora on medium to low resource infrastructures. In Proceedings of the 7th Workshop on the Challenges in the Management of Large Corpora."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 21st Conference on Neural Information Processing Systems.","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Proceedings of the 21st Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"e_1_3_2_1_37_1","volume-title":"LayoutXLM: Multimodal pre-training for multilingual visually-rich document understanding. arXiv preprint arXiv:2104.08836","author":"Xu Yiheng","year":"2021","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 preprint arXiv:2104.08836 (2021)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.201"}],"event":{"name":"CBMI 2023: 20th International Conference on Content-based Multimedia Indexing","acronym":"CBMI 2023","location":"Orleans France"},"container-title":["20th International Conference on Content-based Multimedia Indexing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3617233.3617239","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3617233.3617239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T16:58:35Z","timestamp":1756486715000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3617233.3617239"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,20]]},"references-count":38,"alternative-id":["10.1145\/3617233.3617239","10.1145\/3617233"],"URL":"https:\/\/doi.org\/10.1145\/3617233.3617239","relation":{},"subject":[],"published":{"date-parts":[[2023,9,20]]},"assertion":[{"value":"2023-12-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}