Articles producció científica> Enginyeria Informàtica i Matemàtiques

The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization

  • Identification data

    Identifier: imarina:9287297
    Authors:
    Pilan, IldikoLison, Pierreovrelid, LiljaPapadopoulou, AnthiSanchez, DavidBatet, Montserrat
    Abstract:
    We present a novel benchmark and associated evaluation metrics for assessing the performance of text anonymization methods. Text anonymization, defined as the task of editing a text document to prevent the disclosure of personal information, currently suffers from a shortage of privacy-oriented annotated text resources, making it difficult to properly evaluate the level of privacy protection offered by various anonymization methods. This paper presents TAB (Text Anony-mization Benchmark), a new, open-source annotated corpus developed to address this shortage. The corpus comprises 1,268 English-language court cases from the European Court of Human Rights (ECHR) enriched with comprehensive annotations about the personal information appearing in each document, including their semantic category, identifier type, confidential attributes, and co-reference relations. Compared with previous work, the TAB corpus is designed to go beyond traditional de-identification (which is limited to the detection of predefined semantic categories), and explicitly marks which text spans ought to be masked in order to conceal the identity of the person to be protected. Along with presenting the corpus and its annotation layers, we also propose a set of evaluation metrics that are specifically tailored toward measuring the performance of text anonymization, both in terms of privacy protection and utility preservation. We illustrate the use of the benchmark and the proposed metrics by assessing the empirical performance of several baseline text anonymization models. The full corpus along with its privacy-oriented annotation guidelines, evaluation scripts, and baseline models are available on: https://github.com /NorskRegnesentral/text-anonymization-benchmark.
  • Others:

    Author, as appears in the article.: Pilan, Ildiko; Lison, Pierre; ovrelid, Lilja; Papadopoulou, Anthi; Sanchez, David; Batet, Montserrat
    Department: Enginyeria Informàtica i Matemàtiques
    URV's Author/s: Batet Sanromà, Montserrat / Sánchez Ruenes, David
    Abstract: We present a novel benchmark and associated evaluation metrics for assessing the performance of text anonymization methods. Text anonymization, defined as the task of editing a text document to prevent the disclosure of personal information, currently suffers from a shortage of privacy-oriented annotated text resources, making it difficult to properly evaluate the level of privacy protection offered by various anonymization methods. This paper presents TAB (Text Anony-mization Benchmark), a new, open-source annotated corpus developed to address this shortage. The corpus comprises 1,268 English-language court cases from the European Court of Human Rights (ECHR) enriched with comprehensive annotations about the personal information appearing in each document, including their semantic category, identifier type, confidential attributes, and co-reference relations. Compared with previous work, the TAB corpus is designed to go beyond traditional de-identification (which is limited to the detection of predefined semantic categories), and explicitly marks which text spans ought to be masked in order to conceal the identity of the person to be protected. Along with presenting the corpus and its annotation layers, we also propose a set of evaluation metrics that are specifically tailored toward measuring the performance of text anonymization, both in terms of privacy protection and utility preservation. We illustrate the use of the benchmark and the proposed metrics by assessing the empirical performance of several baseline text anonymization models. The full corpus along with its privacy-oriented annotation guidelines, evaluation scripts, and baseline models are available on: https://github.com /NorskRegnesentral/text-anonymization-benchmark.
    Thematic Areas: Linguistics and language Linguistics Language and linguistics Language & linguistics Filologia, lingüística i sociolingüística Computer science, interdisciplinary applications Computer science, artificial intelligence Computer science applications Ciencias sociales Ciencias humanas Ciência da computação Artificial intelligence Applied linguistics
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    Author's mail: montserrat.batet@urv.cat david.sanchez@urv.cat
    Author identifier: 0000-0001-8174-7592 0000-0001-7275-7887
    Record's date: 2024-10-12
    Papper version: info:eu-repo/semantics/publishedVersion
    Link to the original source: https://direct.mit.edu/coli/article/48/4/1053/112770/The-Text-Anonymization-Benchmark-TAB-A-Dedicated
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Papper original source: Computational Linguistics. 48 (4): 1053-1101
    APA: Pilan, Ildiko; Lison, Pierre; ovrelid, Lilja; Papadopoulou, Anthi; Sanchez, David; Batet, Montserrat (2022). The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization. Computational Linguistics, 48(4), 1053-1101. DOI: 10.1162/coli_a_00458
    Article's DOI: 10.1162/coli_a_00458
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2022
    Publication Type: Journal Publications
  • Keywords:

    Applied Linguistics,Artificial Intelligence,Computer Science Applications,Computer Science, Artificial Intelligence,Computer Science, Interdisciplinary Applications,Language & Linguistics,Language and Linguistics,Linguistics,Linguistics and Language
    Linguistics and language
    Linguistics
    Language and linguistics
    Language & linguistics
    Filologia, lingüística i sociolingüística
    Computer science, interdisciplinary applications
    Computer science, artificial intelligence
    Computer science applications
    Ciencias sociales
    Ciencias humanas
    Ciência da computação
    Artificial intelligence
    Applied linguistics
  • Documents:

  • Cerca a google

    Search to google scholar