@inproceedings{afkanpour-etal-2022-bert,
title = "{BERT} for Long Documents: A Case Study of Automated {ICD} Coding",
author = "Afkanpour, Arash and
Adeel, Shabir and
Bassani, Hansenclever and
Epshteyn, Arkady and
Fan, Hongbo and
Jones, Isaac and
Malihi, Mahan and
Nauth, Adrian and
Sinha, Raj and
Woonna, Sanjana and
Zamani, Shiva and
Kanal, Elli and
Fomitchev, Mikhail and
Cheung, Donny",
editor = "Lavelli, Alberto and
Holderness, Eben and
Jimeno Yepes, Antonio and
Minard, Anne-Lyse and
Pustejovsky, James and
Rinaldi, Fabio",
booktitle = "Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.louhi-1.12",
doi = "10.18653/v1/2022.louhi-1.12",
pages = "100--107",
abstract = "Transformer models have achieved great success across many NLP problems. However, previous studies in automated ICD coding concluded that these models fail to outperform some of the earlier solutions such as CNN-based models. In this paper we challenge this conclusion. We present a simple and scalable method to process long text with the existing transformer models such as BERT. We show that this method significantly improves the previous results reported for transformer models in ICD coding, and is able to outperform one of the prominent CNN-based methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="afkanpour-etal-2022-bert">
<titleInfo>
<title>BERT for Long Documents: A Case Study of Automated ICD Coding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arash</namePart>
<namePart type="family">Afkanpour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shabir</namePart>
<namePart type="family">Adeel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansenclever</namePart>
<namePart type="family">Bassani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arkady</namePart>
<namePart type="family">Epshteyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongbo</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isaac</namePart>
<namePart type="family">Jones</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahan</namePart>
<namePart type="family">Malihi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="family">Nauth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjana</namePart>
<namePart type="family">Woonna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiva</namePart>
<namePart type="family">Zamani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elli</namePart>
<namePart type="family">Kanal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Fomitchev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donny</namePart>
<namePart type="family">Cheung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Lavelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eben</namePart>
<namePart type="family">Holderness</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Jimeno Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Lyse</namePart>
<namePart type="family">Minard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Transformer models have achieved great success across many NLP problems. However, previous studies in automated ICD coding concluded that these models fail to outperform some of the earlier solutions such as CNN-based models. In this paper we challenge this conclusion. We present a simple and scalable method to process long text with the existing transformer models such as BERT. We show that this method significantly improves the previous results reported for transformer models in ICD coding, and is able to outperform one of the prominent CNN-based methods.</abstract>
<identifier type="citekey">afkanpour-etal-2022-bert</identifier>
<identifier type="doi">10.18653/v1/2022.louhi-1.12</identifier>
<location>
<url>https://aclanthology.org/2022.louhi-1.12</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>100</start>
<end>107</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BERT for Long Documents: A Case Study of Automated ICD Coding
%A Afkanpour, Arash
%A Adeel, Shabir
%A Bassani, Hansenclever
%A Epshteyn, Arkady
%A Fan, Hongbo
%A Jones, Isaac
%A Malihi, Mahan
%A Nauth, Adrian
%A Sinha, Raj
%A Woonna, Sanjana
%A Zamani, Shiva
%A Kanal, Elli
%A Fomitchev, Mikhail
%A Cheung, Donny
%Y Lavelli, Alberto
%Y Holderness, Eben
%Y Jimeno Yepes, Antonio
%Y Minard, Anne-Lyse
%Y Pustejovsky, James
%Y Rinaldi, Fabio
%S Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F afkanpour-etal-2022-bert
%X Transformer models have achieved great success across many NLP problems. However, previous studies in automated ICD coding concluded that these models fail to outperform some of the earlier solutions such as CNN-based models. In this paper we challenge this conclusion. We present a simple and scalable method to process long text with the existing transformer models such as BERT. We show that this method significantly improves the previous results reported for transformer models in ICD coding, and is able to outperform one of the prominent CNN-based methods.
%R 10.18653/v1/2022.louhi-1.12
%U https://aclanthology.org/2022.louhi-1.12
%U https://doi.org/10.18653/v1/2022.louhi-1.12
%P 100-107
Markdown (Informal)
[BERT for Long Documents: A Case Study of Automated ICD Coding](https://aclanthology.org/2022.louhi-1.12) (Afkanpour et al., Louhi 2022)
ACL
- Arash Afkanpour, Shabir Adeel, Hansenclever Bassani, Arkady Epshteyn, Hongbo Fan, Isaac Jones, Mahan Malihi, Adrian Nauth, Raj Sinha, Sanjana Woonna, Shiva Zamani, Elli Kanal, Mikhail Fomitchev, and Donny Cheung. 2022. BERT for Long Documents: A Case Study of Automated ICD Coding. In Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI), pages 100–107, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.