{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T00:25:08Z","timestamp":1773447908630,"version":"3.50.1"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031139444","type":"print"},{"value":"9783031139451","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-13945-1_12","type":"book-chapter","created":{"date-parts":[[2022,9,13]],"date-time":"2022-09-13T23:02:54Z","timestamp":1663110174000},"page":"157-171","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Automatic Evaluation of Disclosure Risks of Text Anonymization Methods"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7254-2560","authenticated-orcid":false,"given":"Benet","family":"Manzanares-Salor","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7275-7887","authenticated-orcid":false,"given":"David","family":"S\u00e1nchez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7649-0689","authenticated-orcid":false,"given":"Pierre","family":"Lison","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,14]]},"reference":[{"key":"12_CR1","unstructured":"Regulation (EU) 2016\/679 of the European Parliament and of the Council of 27 April on the Protection of Natural Persons with Regard to the Processing of Personal Data and on the Free Movement of Such Data and Repealing Directive 95\/46\/EC. In: Commission, E. (ed.) (2016)"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Li, N., Li, T., Venkatasubramanian, S.: t-closeness: privacy beyond k-anonymity and l-diversity. In: 2007 IEEE 23rd International Conference on Data Engineering, pp. 106\u2013115. IEEE (2007)","DOI":"10.1109\/ICDE.2007.367856"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Machanavajjhala, A., Kifer, D., Gehrke, J., Venkitasubramaniam, M.: l-diversity: privacy beyond k-anonymity. ACM Trans. Knowl. Disc. Data (TKDD) 1, 3-es (2007)","DOI":"10.1145\/1217299.1217302"},{"key":"12_CR4","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1142\/S0218488502001648","volume":"10","author":"L Sweeney","year":"2002","unstructured":"Sweeney, L.: k-anonymity: A model for protecting privacy. Int. J. Uncertain. Fuzz. Knowl. Based Syst. 10, 557\u2013570 (2002)","journal-title":"Int. J. Uncertain. Fuzz. Knowl. Based Syst."},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Dwork, C.: Differential privacy. In: International Colloquium on Automata, Languages, and Programming, pp. 1\u201312. Springer (2006)","DOI":"10.1007\/11787006_1"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Lison, P., Pil\u00e1n, I., S\u00e1nchez, D., Batet, M., \u00d8vrelid, L.: Anonymisation models for text data: state of the art, challenges and future directions. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, vol. 1, Long Papers, pp. 4188\u20134203 (2021)","DOI":"10.18653\/v1\/2021.acl-long.323"},{"key":"12_CR7","doi-asserted-by":"publisher","first-page":"1490","DOI":"10.3390\/sym13081490","volume":"13","author":"GM Cs\u00e1nyi","year":"2021","unstructured":"Cs\u00e1nyi, G.M., Nagy, D., V\u00e1gi, R., Vad\u00e1sz, J.P., Orosz, T.: Challenges and open problems of legal document anonymization. Symmetry 13, 1490 (2021)","journal-title":"Symmetry"},{"key":"12_CR8","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1016\/j.ijmedinf.2010.09.007","volume":"79","author":"J Aberdeen","year":"2010","unstructured":"Aberdeen, J., et al.: The MITRE identification scrubber toolkit: design, training, and assessment. Int. J. Med. Informatics 79, 849\u2013859 (2010)","journal-title":"Int. J. Med. Informatics"},{"key":"12_CR9","unstructured":"Chen, A., Jonnagaddala, J., Nekkantti, C., Liaw, S.-T.: Generation of surrogates for de-identification of electronic health records. In: MEDINFO 2019: Health and Wellbeing e-Networks for All, pp. 70\u201373. IOS Press (2019)"},{"key":"12_CR10","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1093\/jamia\/ocw156","volume":"24","author":"F Dernoncourt","year":"2017","unstructured":"Dernoncourt, F., Lee, J.Y., Uzuner, O., Szolovits, P.: De-identification of patient notes with recurrent neural networks. J. Am. Med. Inform. Assoc. 24, 596\u2013606 (2017)","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., Bulgarelli, L., Pollard, T.J.: Deidentification of free-text medical records using pre-trained bidirectional transformers. In: Proceedings of the ACM Conference on Health, Inference, and Learning, pp. 214\u2013221 (2020)","DOI":"10.1145\/3368555.3384455"},{"key":"12_CR12","doi-asserted-by":"publisher","first-page":"S34","DOI":"10.1016\/j.jbi.2017.05.023","volume":"75","author":"Z Liu","year":"2017","unstructured":"Liu, Z., Tang, B., Wang, X., Chen, Q.: De-identification of clinical notes via recurrent neural network and conditional random field. J. Biomed. Inform. 75, S34\u2013S42 (2017)","journal-title":"J. Biomed. Inform."},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Mamede, N., Baptista, J., Dias, F.: Automated anonymization of text documents. In: 2016 IEEE Congress on Evolutionary Computation (CEC), pp. 1287\u20131294. IEEE (2016)","DOI":"10.1109\/CEC.2016.7743936"},{"key":"12_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2288-10-70","volume":"10","author":"SM Meystre","year":"2010","unstructured":"Meystre, S.M., Friedlin, F.J., South, B.R., Shen, S., Samore, M.H.: Automatic de-identification of textual documents in the electronic health record: a review of recent research. BMC Med. Res. Methodol. 10, 1\u201316 (2010)","journal-title":"BMC Med. Res. Methodol."},{"key":"12_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1472-6947-8-32","volume":"8","author":"I Neamatullah","year":"2008","unstructured":"Neamatullah, I., et al.: Automated de-identification of free-text medical records. BMC Med. Inform. Decis. Mak. 8, 1\u201317 (2008)","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Reddy, S., Knight, K.: Obfuscating gender in social media writing. In: Proceedings of the First Workshop on NLP and Computational Social Science, pp. 17\u201326 (2016)","DOI":"10.18653\/v1\/W16-5603"},{"key":"12_CR17","unstructured":"Sweeney, L.: Replacing personally-identifying information in medical records, the Scrub system. In: Proceedings of the AMIA Annual Fall Symposium, p. 333. American Medical Informatics Association (1996)"},{"key":"12_CR18","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1197\/jamia.M2441","volume":"14","author":"G Szarvas","year":"2007","unstructured":"Szarvas, G., Farkas, R., Busa-Fekete, R.: State-of-the-art anonymization of medical records using an iterative machine learning framework. J. Am. Med. Inform. Assoc. 14, 574\u2013580 (2007)","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Xu, Q., Qu, L., Xu, C., Cui, R.: Privacy-aware text rewriting. In: Proceedings of the 12th International Conference on Natural Language Generation, pp. 247\u2013257 (2019)","DOI":"10.18653\/v1\/W19-8633"},{"key":"12_CR20","doi-asserted-by":"publisher","first-page":"S30","DOI":"10.1016\/j.jbi.2015.06.015","volume":"58","author":"H Yang","year":"2015","unstructured":"Yang, H., Garibaldi, J.M.: Automatic detection of protected health information from clinic narratives. J. Biomed. Inform. 58, S30\u2013S38 (2015)","journal-title":"J. Biomed. Inform."},{"key":"12_CR21","first-page":"148","volume":"67","author":"D S\u00e1nchez","year":"2016","unstructured":"S\u00e1nchez, D., Batet, M.: C-sanitized: a privacy model for document redaction and sanitization. J. Am. Soc. Inf. Sci. 67, 148\u2013163 (2016)","journal-title":"J. Am. Soc. Inf. Sci."},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Mosallanezhad, A., Beigi, G., Liu, H.: Deep reinforcement learning-based text anonymization against private-attribute inference. 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), pp. 2360\u20132369 (2019)","DOI":"10.18653\/v1\/D19-1240"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Chakaravarthy, V.T., Gupta, H., Roy, P., Mohania, M.K.: Efficient techniques for document sanitization. In: Proceedings of the 17th ACM Conference on Information and Knowledge Management, pp. 843\u2013852 (2008)","DOI":"10.1145\/1458082.1458194"},{"key":"12_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/978-3-030-17138-4_6","volume-title":"Principles of Security and Trust","author":"N Fernandes","year":"2019","unstructured":"Fernandes, N., Dras, M., McIver, A.: Generalised differential privacy for text document processing. In: Nielson, F., Sands, D. (eds.) Principles of Security and Trust. LNCS, vol. 11426, pp. 123\u2013148. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-17138-4_6"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Cumby, C., Ghani, R.: A machine learning based system for semi-automatically redacting documents. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1628\u20131635 (2011)","DOI":"10.1609\/aaai.v25i2.18851"},{"key":"12_CR26","first-page":"505","volume":"5","author":"B Anandan","year":"2012","unstructured":"Anandan, B., Clifton, C., Jiang, W., Murugesan, M., Pastrana-Camacho, P., Si, L.: t-Plausibility: generalizing words to desensitize text. Trans. Data Priv. 5, 505\u2013534 (2012)","journal-title":"Trans. Data Priv."},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Hassan, F., Sanchez, D., Domingo-Ferrer, J.: Utility-preserving privacy protection of textual documents via word embeddings. IEEE Trans. Knowl. Data Eng. 1 (2021)","DOI":"10.1109\/TKDE.2021.3076632"},{"key":"12_CR28","doi-asserted-by":"publisher","DOI":"10.1002\/9781118348239","volume-title":"Statistical Disclosure Control","author":"A Hundepool","year":"2012","unstructured":"Hundepool, A., et al.: Statistical Disclosure Control. Wiley, New York (2012)"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Pil\u00e1n, I., Lison, P., \u00d8vrelid, L., Papadopoulou, A., S\u00e1nchez, D., Batet, M.: The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization. arXiv preprint arXiv:2202.00443 (2022)","DOI":"10.1162\/coli_a_00458"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Domingo-Ferrer, J., Torra, V.J.S.: Computing: disclosure risk assessment in statistical microdata protection via advanced record linkage. Statist. Comput. 13, 343\u2013354 (2003)","DOI":"10.1023\/A:1025666923033"},{"key":"12_CR31","unstructured":"Nin Guerrero, J., Herranz Sotoca, J., Torra i Revent\u00f3s, V.: On method-specific record linkage for risk assessment. In: Proceedings of the Joint UNECE\/Eurostat Work Session on Statistical Data Confidentiality, pp. 1\u201312 (2007)"},{"key":"12_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/11930242_20","volume-title":"Privacy in Statistical Databases","author":"V Torra","year":"2006","unstructured":"Torra, V., Abowd, J.M., Domingo-Ferrer, J.: Using Mahalanobis distance-based record linkage for disclosure risk assessment. In: DomingoFerrer, J., Franconi, L. (eds.) Privacy in Statistical Databases. LNCS, vol. 4302, pp. 233\u2013242. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11930242_20"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Torra, V., Stokes, K.J.I.J.o.U., Fuzziness, Systems, K.-B.: A formalization of record linkage and its application to data protection. Int. J. Uncert. Fuzz. Knowl. Based Syst. 20, 907\u2013919 (2012)","DOI":"10.1142\/S0218488512400302"},{"key":"12_CR34","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"12_CR35","unstructured":"Mozes, M., Kleinberg, B.J.: No Intruder, no Validity: Evaluation Criteria for Privacy-Preserving Text Anonymization (2021)"},{"key":"12_CR36","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio, Y., Ducharme, R., Vincent, P., Jauvin, C.: A neural probabilistic language model. J. Mach. Learn. Res. 3, 1137\u20131155 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liu, Z., Chua, T.-S., Sun, M.: Topical word embeddings. In: Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)","DOI":"10.1609\/aaai.v29i1.9522"},{"key":"12_CR38","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"12_CR39","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"12_CR40","doi-asserted-by":"publisher","first-page":"113679","DOI":"10.1016\/j.eswa.2020.113679","volume":"165","author":"WS El-Kassas","year":"2021","unstructured":"El-Kassas, W.S., Salama, C.R., Rafea, A.A., Mohamed, H.K.: Automatic text summarization: a comprehensive survey. Expert Syst. Appl. 165, 113679 (2021)","journal-title":"Expert Syst. Appl."},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J.R., Bethard, S., McClosky, D.: The Stanford CoreNLP natural language processing toolkit. In: Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp. 55\u201360 (2014)","DOI":"10.3115\/v1\/P14-5010"},{"key":"12_CR42","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.engappai.2016.12.013","volume":"59","author":"D S\u00e1nchez","year":"2017","unstructured":"S\u00e1nchez, D., Batet, M.: Toward sensitive document release with privacy guarantees. Eng. Appl. Artif. Intell. 59, 23\u201334 (2017)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"12_CR43","unstructured":"Staddon, J., Golle, P., Zimny, B.: Web-based inference detection. In: USENIX Security Symposium (2007)"}],"container-title":["Lecture Notes in Computer Science","Privacy in Statistical Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-13945-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T11:37:23Z","timestamp":1710329843000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-13945-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031139444","9783031139451"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-13945-1_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"14 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Privacy in Statistical Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Paris","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"psd2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/crises-deim.urv.cat\/psd2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"25","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"56% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.1","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}