@inproceedings{blanco-etal-2021-contribution,
title = "On the Contribution of Per-{ICD} Attention Mechanisms to Classify Health Records in Languages with Fewer Resources than {E}nglish",
author = "Blanco, Alberto and
Remmer, Sonja and
P{\'e}rez, Alicia and
Dalianis, Hercules and
Casillas, Arantza",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)",
month = sep,
year = "2021",
address = "Held Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.ranlp-1.20",
pages = "165--172",
abstract = "We introduce a multi-label text classifier with per-label attention for the classification of Electronic Health Records according to the International Classification of Diseases. We apply the model on two Electronic Health Records datasets with Discharge Summaries in two languages with fewer resources than English, Spanish and Swedish. Our model leverages the BERT Multilingual model (specifically the Wikipedia, as the model have been trained with 104 languages, including Spanish and Swedish, with the largest Wikipedia dumps) to share the language modelling capabilities across the languages. With the per-label attention, the model can compute the relevance of each word from the EHR towards the prediction of each label. For the experimental framework, we apply 157 labels from Chapter XI {--} Diseases of the Digestive System of the ICD, which makes the attention especially important as the model has to discriminate between similar diseases. 1 \url{https://github.com/google-research/bert/blob/master/multilingual.md#list-of-languages}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="blanco-etal-2021-contribution">
<titleInfo>
<title>On the Contribution of Per-ICD Attention Mechanisms to Classify Health Records in Languages with Fewer Resources than English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Blanco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonja</namePart>
<namePart type="family">Remmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Pérez</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>
<name type="personal">
<namePart type="given">Arantza</namePart>
<namePart type="family">Casillas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Held Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a multi-label text classifier with per-label attention for the classification of Electronic Health Records according to the International Classification of Diseases. We apply the model on two Electronic Health Records datasets with Discharge Summaries in two languages with fewer resources than English, Spanish and Swedish. Our model leverages the BERT Multilingual model (specifically the Wikipedia, as the model have been trained with 104 languages, including Spanish and Swedish, with the largest Wikipedia dumps) to share the language modelling capabilities across the languages. With the per-label attention, the model can compute the relevance of each word from the EHR towards the prediction of each label. For the experimental framework, we apply 157 labels from Chapter XI – Diseases of the Digestive System of the ICD, which makes the attention especially important as the model has to discriminate between similar diseases. 1 https://github.com/google-research/bert/blob/master/multilingual.md#list-of-languages</abstract>
<identifier type="citekey">blanco-etal-2021-contribution</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-1.20</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>165</start>
<end>172</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Contribution of Per-ICD Attention Mechanisms to Classify Health Records in Languages with Fewer Resources than English
%A Blanco, Alberto
%A Remmer, Sonja
%A Pérez, Alicia
%A Dalianis, Hercules
%A Casillas, Arantza
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F blanco-etal-2021-contribution
%X We introduce a multi-label text classifier with per-label attention for the classification of Electronic Health Records according to the International Classification of Diseases. We apply the model on two Electronic Health Records datasets with Discharge Summaries in two languages with fewer resources than English, Spanish and Swedish. Our model leverages the BERT Multilingual model (specifically the Wikipedia, as the model have been trained with 104 languages, including Spanish and Swedish, with the largest Wikipedia dumps) to share the language modelling capabilities across the languages. With the per-label attention, the model can compute the relevance of each word from the EHR towards the prediction of each label. For the experimental framework, we apply 157 labels from Chapter XI – Diseases of the Digestive System of the ICD, which makes the attention especially important as the model has to discriminate between similar diseases. 1 https://github.com/google-research/bert/blob/master/multilingual.md#list-of-languages
%U https://aclanthology.org/2021.ranlp-1.20
%P 165-172
Markdown (Informal)
[On the Contribution of Per-ICD Attention Mechanisms to Classify Health Records in Languages with Fewer Resources than English](https://aclanthology.org/2021.ranlp-1.20) (Blanco et al., RANLP 2021)
ACL