@inproceedings{brathen-etal-2021-creating,
title = "Creating and Evaluating a Synthetic {N}orwegian Clinical Corpus for De-Identification",
author = "Br{\r{a}}then, Synn{\o}ve and
Wie, Wilhelm and
Dalianis, Hercules",
editor = "Dobnik, Simon and
{\O}vrelid, Lilja",
booktitle = "Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may # " 31--2 " # jun,
year = "2021",
address = "Reykjavik, Iceland (Online)",
publisher = {Link{\"o}ping University Electronic Press, Sweden},
url = "https://aclanthology.org/2021.nodalida-main.22/",
pages = "222--230",
abstract = "Building tools to remove sensitive information such as personal names, addresses, and telephone numbers - so called Protected Health Information (PHI) - from clinical free text is an important task to make clinical texts available for research. These de-identification tools must be assessed regarding their quality in the form of the measurements precision and re- call. To assess such tools, gold standards - annotated clinical text - must be available. Such gold standards exist for larger languages. For Norwegian, how- ever, there are no such resources. Therefore, an already existing Norwegian synthetic clinical corpus, NorSynthClinical, has been extended with PHIs and annotated by two annotators, obtaining an inter-annotator agreement of 0.94 F1-measure. In total, the corpus has 409 annotated PHI instances and is called NorSynthClinical PHI. A de-identification hybrid tool (machine learning and rule-based meth- ods) for Norwegian was developed and trained with open available resources, and obtained an overall F1-measure of 0.73 and a recall of 0.62, when tested using NorSynthClinical PHI. NorSynthClinical PHI is made open and available at Github to be used by the research community."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brathen-etal-2021-creating">
<titleInfo>
<title>Creating and Evaluating a Synthetic Norwegian Clinical Corpus for De-Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Synnøve</namePart>
<namePart type="family">Bråthen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wilhelm</namePart>
<namePart type="family">Wie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hercules</namePart>
<namePart type="family">Dalianis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-may 31–2 jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Linköping University Electronic Press, Sweden</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Building tools to remove sensitive information such as personal names, addresses, and telephone numbers - so called Protected Health Information (PHI) - from clinical free text is an important task to make clinical texts available for research. These de-identification tools must be assessed regarding their quality in the form of the measurements precision and re- call. To assess such tools, gold standards - annotated clinical text - must be available. Such gold standards exist for larger languages. For Norwegian, how- ever, there are no such resources. Therefore, an already existing Norwegian synthetic clinical corpus, NorSynthClinical, has been extended with PHIs and annotated by two annotators, obtaining an inter-annotator agreement of 0.94 F1-measure. In total, the corpus has 409 annotated PHI instances and is called NorSynthClinical PHI. A de-identification hybrid tool (machine learning and rule-based meth- ods) for Norwegian was developed and trained with open available resources, and obtained an overall F1-measure of 0.73 and a recall of 0.62, when tested using NorSynthClinical PHI. NorSynthClinical PHI is made open and available at Github to be used by the research community.</abstract>
<identifier type="citekey">brathen-etal-2021-creating</identifier>
<location>
<url>https://aclanthology.org/2021.nodalida-main.22/</url>
</location>
<part>
<date>2021-may 31–2 jun</date>
<extent unit="page">
<start>222</start>
<end>230</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating and Evaluating a Synthetic Norwegian Clinical Corpus for De-Identification
%A Bråthen, Synnøve
%A Wie, Wilhelm
%A Dalianis, Hercules
%Y Dobnik, Simon
%Y Øvrelid, Lilja
%S Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2021
%8 may 31–2 jun
%I Linköping University Electronic Press, Sweden
%C Reykjavik, Iceland (Online)
%F brathen-etal-2021-creating
%X Building tools to remove sensitive information such as personal names, addresses, and telephone numbers - so called Protected Health Information (PHI) - from clinical free text is an important task to make clinical texts available for research. These de-identification tools must be assessed regarding their quality in the form of the measurements precision and re- call. To assess such tools, gold standards - annotated clinical text - must be available. Such gold standards exist for larger languages. For Norwegian, how- ever, there are no such resources. Therefore, an already existing Norwegian synthetic clinical corpus, NorSynthClinical, has been extended with PHIs and annotated by two annotators, obtaining an inter-annotator agreement of 0.94 F1-measure. In total, the corpus has 409 annotated PHI instances and is called NorSynthClinical PHI. A de-identification hybrid tool (machine learning and rule-based meth- ods) for Norwegian was developed and trained with open available resources, and obtained an overall F1-measure of 0.73 and a recall of 0.62, when tested using NorSynthClinical PHI. NorSynthClinical PHI is made open and available at Github to be used by the research community.
%U https://aclanthology.org/2021.nodalida-main.22/
%P 222-230
Markdown (Informal)
[Creating and Evaluating a Synthetic Norwegian Clinical Corpus for De-Identification](https://aclanthology.org/2021.nodalida-main.22/) (Bråthen et al., NoDaLiDa 2021)
ACL