MAPA Project: Ready-to-Go Open-Source Datasets and Deep Learning Technology to Remove Identifying Information from Text Documents
Egileak: Victoria Arranz Khalid Choukri Lucie Gianola Cyril Grouin Manuel Herranz Patrick Paroubek Pierre Zweigenbaum
Data: 24.06.2022
Abstract
This paper presents the outcomes of the MAPA project, a set of annotated corpora for 24 languages of the European Union and an open-source customisable toolkit able to detect and substitute sensitive information in text documents from any domain, using state-of-the art, deep learning-based named entity recognition techniques. In the context of the project, the toolkit has been developed and tested on administrative, legal and medical documents, obtaining state-of-the-art results. As a result of the project, 24 dataset packages have been released and the de-identification toolkit is available as open source.
BIB_text
title = {MAPA Project: Ready-to-Go Open-Source Datasets and Deep Learning Technology to Remove Identifying Information from Text Documents},
pages = {64-72},
keywds = {
anonymisation, de-identification, sensitive information, deep learning, BERT, NER, annotated data
}
abstract = {
This paper presents the outcomes of the MAPA project, a set of annotated corpora for 24 languages of the European Union and an open-source customisable toolkit able to detect and substitute sensitive information in text documents from any domain, using state-of-the art, deep learning-based named entity recognition techniques. In the context of the project, the toolkit has been developed and tested on administrative, legal and medical documents, obtaining state-of-the-art results. As a result of the project, 24 dataset packages have been released and the de-identification toolkit is available as open source.
}
date = {2022-06-24},
}
