Evaluating Dutch Named Entity Recognition and De-identification Methods in the Human Resources Domain

C. van Toledo, F. van Dijk, M. Spruit

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Abstract

    The human resource (HR) domain contains various types of privacy-sensitive textual data, such as e-mail correspondence and performance appraisal. Doing research on these documents brings several challenges, one of them anonymisation. In this paper, we evaluate the current Dutch text de-identification methods for the HR domain in three steps. First, by updating one of these methods with the latest named entity recognition (NER) models. The result is that the NER model based on the CoNLL 2002 corpus in combination with the BERTje transformer give the best combination for suppressing persons (recall 0.94) and locations (recall 0.82). For suppressing gender, DEDUCE is performing best (recall 0.53). Second NER evaluation is based on both strict de-identification of entities (a person must be suppressed as a person) and third evaluation on a loose sense of de-identification (no matter what how a person is suppressed, as long it is suppressed).
    Original languageEnglish
    Title of host publication10th International Conference on Advances in Computing and Information Technology (ACITY 2020), November 28~29, 2020, London, United Kingdom
    EditorsDavid C. Wyld, Dhinaharan Nagamalai
    PublisherAIRCC Publishing Corporation
    Pages239–249
    Volume10
    ISBN (Print)978-1-925953-29-9
    DOIs
    Publication statusPublished - Nov 2020

    Bibliographical note

    Volume 10, Number 15, November 2020

    Keywords

    • Named Entity Recognition
    • Dutch
    • NER
    • BERT
    • evaluation
    • de-identification

    Fingerprint

    Dive into the research topics of 'Evaluating Dutch Named Entity Recognition and De-identification Methods in the Human Resources Domain'. Together they form a unique fingerprint.

    Cite this