{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:49:31Z","timestamp":1743000571724,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031777301"},{"type":"electronic","value":"9783031777318"}],"license":[{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-77731-8_40","type":"book-chapter","created":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T16:43:20Z","timestamp":1732034600000},"page":"447-459","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic PDF Document Classification with\u00a0Machine Learning"],"prefix":"10.1007","author":[{"given":"S\u00f3crates Ll\u00e1cer","family":"Luna","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dario","family":"Garigliotti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fernando Mart\u00ednez","family":"Plumed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C\u00e9sar Ferri","family":"Ram\u00edrez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,14]]},"reference":[{"key":"40_CR1","unstructured":"Aas, K., Eikvil, L.: Text categorisation: a survey (1999)"},{"key":"40_CR2","unstructured":"Adhikari, A., Ram, A., Tang, R., Lin, J.: DocBERT: BERT for document classification. arXiv:1904.08398 (2019)"},{"key":"40_CR3","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: LongFormer: the long-document transformer. arXiv:2004.05150 (2020)"},{"issue":"2","key":"40_CR4","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1145\/321160.321165","volume":"10","author":"H Borko","year":"1963","unstructured":"Borko, H., Bernick, M.: Automatic document classification. J. ACM (JACM) 10(2), 151\u2013162 (1963)","journal-title":"J. ACM (JACM)"},{"key":"40_CR5","unstructured":"Bradski, G.: The OpenCV library. Dr. Dobb\u2019s J.: Softw. Tools Prof. Program. 25(11), 120\u2013123 (2000)"},{"issue":"1","key":"40_CR6","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Mach. Learn. 45(1), 5\u201332 (2001)","journal-title":"Mach. Learn."},{"issue":"7","key":"40_CR7","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1109\/34.506792","volume":"18","author":"RG Casey","year":"1996","unstructured":"Casey, R.G., Lecolinet, E.: A survey of methods and strategies in character segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 18(7), 690\u2013706 (1996)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Chalkidis, I., Fergadiotis, M., Kotitsas, S., Malakasiotis, P., Aletras, N., Androutsopoulos, I.: An empirical study on large-scale multi-label text classification including few and zero-shot labels. arXiv:2010.01653 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.607"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785\u2013794 (2016)","DOI":"10.1145\/2939672.2939785"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Christian, H., Agus, M.P., Suhartono, D.: Single document automatic text summarization using term frequency-inverse document frequency (TF-IDF). ComTech: Comput. Math. Eng. Appl. 7(4), 285\u2013294 (2016)","DOI":"10.21512\/comtech.v7i4.3746"},{"key":"40_CR11","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805 (2018)"},{"key":"40_CR12","first-page":"12792","volume":"33","author":"M Ding","year":"2020","unstructured":"Ding, M., Zhou, C., Yang, H., Tang, J.: CogLTX: applying BERT to long texts. Adv. Neural. Inf. Process. Syst. 33, 12792\u201312804 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"40_CR13","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.patrec.2008.08.010","volume":"30","author":"C Ferri","year":"2009","unstructured":"Ferri, C., Hern\u00e1ndez-Orallo, J., Modroiu, R.: An experimental comparison of performance measures for classification. Pattern Recogn. Lett. 30(1), 27\u201338 (2009)","journal-title":"Pattern Recogn. Lett."},{"key":"40_CR14","unstructured":"Hinton, G.E., Roweis, S.: Stochastic neighbor embedding. Adv. Neural. Inf. Process. Syst. 15 (2002)"},{"key":"40_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/BFb0026683","volume-title":"Machine Learning: ECML-98","author":"T Joachims","year":"1998","unstructured":"Joachims, T.: Text categorization with support vector machines: learning with many relevant features. In: N\u00e9dellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol. 1398, pp. 137\u2013142. Springer, Heidelberg (1998). https:\/\/doi.org\/10.1007\/BFb0026683"},{"issue":"1","key":"40_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2016.35","volume":"3","author":"AE Johnson","year":"2016","unstructured":"Johnson, A.E., et al.: MIMIC-III, a freely accessible critical care database. Sci. Data 3(1), 1\u20139 (2016)","journal-title":"Sci. Data"},{"key":"40_CR17","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv:1907.11692 (2019)"},{"key":"40_CR18","doi-asserted-by":"crossref","unstructured":"Malathi, T., Selvamuthukumaran, D., Chandar, C.D., Niranjan, V., Swashthika, A.: An experimental performance analysis on robotics process automation (RPA) with open source OCR engines: Microsoft OCR and google tesseract OCR. In: IOP Conference Series: Materials Science and Engineering, vol.\u00a01059, p. 012004 (2021)","DOI":"10.1088\/1757-899X\/1059\/1\/012004"},{"key":"40_CR19","unstructured":"McCallum, A., Nigam, K., et\u00a0al.: A comparison of event models for naive bayes text classification. In: AAAI-98 Workshop on Learning for Text Categorization, Madison, WI, vol.\u00a0752, pp. 41\u201348 (1998)"},{"key":"40_CR20","unstructured":"OpenCV Contributors: OpenCV Documentation. https:\/\/docs.opencv.org\/4.x\/. Accessed 17 July 2024"},{"key":"40_CR21","unstructured":"Potts, J.: Alfresco Developer Guide. Packt Publishing Ltd. (2008)"},{"key":"40_CR22","unstructured":"PyTesseract Contributors: Pytesseract: A python wrapper for Google\u2019s tesseract-OCR engine (2024). https:\/\/pypi.org\/project\/pytesseract\/. Accessed 08 July 2024"},{"issue":"1","key":"40_CR23","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/BF00116251","volume":"1","author":"JR Quinlan","year":"1986","unstructured":"Quinlan, J.R.: Induction of decision trees. Mach. Learn. 1(1), 81\u2013106 (1986)","journal-title":"Mach. Learn."},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the tesseract OCR engine. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), vol.\u00a02, pp. 629\u2013633. IEEE (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"40_CR25","doi-asserted-by":"crossref","unstructured":"Srivastava, S., Verma, A., Sharma, S.: Optical character recognition techniques: a review. In: 2022 IEEE International Students\u2019 Conference on Electrical, Electronics and Computer Science (SCEECS), pp.\u00a01\u20136. IEEE (2022)","DOI":"10.1109\/SCEECS54111.2022.9740911"},{"key":"40_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-77242-4","volume-title":"Support Vector Machines","author":"I Steinwart","year":"2008","unstructured":"Steinwart, I., Christmann, A.: Support Vector Machines. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-0-387-77242-4"},{"key":"40_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural. Inf. Process. Syst. 5998\u20136008 (2017)"},{"key":"40_CR28","unstructured":"Wolf, T., et\u00a0al.: HuggingFace\u2019s transformers: state-of-the-art natural language processing. arXiv:1910.03771 (2019)"},{"key":"40_CR29","unstructured":"Zaheer, M., et al.: Big bird: transformers for longer sequences. Adv. Neural. Inf. Process. Syst. 33, 17283\u201317297 (2020)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Data Engineering and Automated Learning \u2013 IDEAL 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77731-8_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T16:48:10Z","timestamp":1732034890000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77731-8_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,14]]},"ISBN":["9783031777301","9783031777318"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77731-8_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,14]]},"assertion":[{"value":"14 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IDEAL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Data Engineering and Automated Learning","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Valencia","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ideal2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}