@inproceedings{ziletti-etal-2022-medical,
title = "{M}edical Coding with Biomedical Transformer Ensembles and Zero/Few-shot Learning",
author = "Ziletti, Angelo and
Akbik, Alan and
Berns, Christoph and
Herold, Thomas and
Legler, Marion and
Viell, Martina",
editor = "Loukina, Anastassia and
Gangadharaiah, Rashmi and
Min, Bonan",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track",
month = jul,
year = "2022",
address = "Hybrid: Seattle, Washington + Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-industry.21",
doi = "10.18653/v1/2022.naacl-industry.21",
pages = "176--187",
abstract = "Medical coding (MC) is an essential pre-requisite for reliable data retrieval and reporting. Given a free-text \textit{reported term} (RT) such as {``}pain of right thigh to the knee{''}, the task is to identify the matching \textit{lowest-level term} (LLT) {--}in this case {``}unilateral leg pain{''}{--} from a very large and continuously growing repository of standardized medical terms. However, automating this task is challenging due to a large number of LLT codes (as of writing over $80\,000$), limited availability of training data for long tail/emerging classes, and the general high accuracy demands of the medical domain.With this paper, we introduce the MC task, discuss its challenges, and present a novel approach called xTARS that combines traditional BERT-based classification with a recent zero/few-shot learning approach (TARS). We present extensive experiments that show that our combined approach outperforms strong baselines, especially in the few-shot regime. The approach is developed and deployed at Bayer, live since November 2021. As we believe our approach potentially promising beyond MC, and to ensure reproducibility, we release the code to the research community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ziletti-etal-2022-medical">
<titleInfo>
<title>Medical Coding with Biomedical Transformer Ensembles and Zero/Few-shot Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Angelo</namePart>
<namePart type="family">Ziletti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Akbik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="family">Berns</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Herold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marion</namePart>
<namePart type="family">Legler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martina</namePart>
<namePart type="family">Viell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastassia</namePart>
<namePart type="family">Loukina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Gangadharaiah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bonan</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid: Seattle, Washington + Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Medical coding (MC) is an essential pre-requisite for reliable data retrieval and reporting. Given a free-text reported term (RT) such as “pain of right thigh to the knee”, the task is to identify the matching lowest-level term (LLT) –in this case “unilateral leg pain”– from a very large and continuously growing repository of standardized medical terms. However, automating this task is challenging due to a large number of LLT codes (as of writing over 80\,000), limited availability of training data for long tail/emerging classes, and the general high accuracy demands of the medical domain.With this paper, we introduce the MC task, discuss its challenges, and present a novel approach called xTARS that combines traditional BERT-based classification with a recent zero/few-shot learning approach (TARS). We present extensive experiments that show that our combined approach outperforms strong baselines, especially in the few-shot regime. The approach is developed and deployed at Bayer, live since November 2021. As we believe our approach potentially promising beyond MC, and to ensure reproducibility, we release the code to the research community.</abstract>
<identifier type="citekey">ziletti-etal-2022-medical</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-industry.21</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-industry.21</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>176</start>
<end>187</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Medical Coding with Biomedical Transformer Ensembles and Zero/Few-shot Learning
%A Ziletti, Angelo
%A Akbik, Alan
%A Berns, Christoph
%A Herold, Thomas
%A Legler, Marion
%A Viell, Martina
%Y Loukina, Anastassia
%Y Gangadharaiah, Rashmi
%Y Min, Bonan
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid: Seattle, Washington + Online
%F ziletti-etal-2022-medical
%X Medical coding (MC) is an essential pre-requisite for reliable data retrieval and reporting. Given a free-text reported term (RT) such as “pain of right thigh to the knee”, the task is to identify the matching lowest-level term (LLT) –in this case “unilateral leg pain”– from a very large and continuously growing repository of standardized medical terms. However, automating this task is challenging due to a large number of LLT codes (as of writing over 80\,000), limited availability of training data for long tail/emerging classes, and the general high accuracy demands of the medical domain.With this paper, we introduce the MC task, discuss its challenges, and present a novel approach called xTARS that combines traditional BERT-based classification with a recent zero/few-shot learning approach (TARS). We present extensive experiments that show that our combined approach outperforms strong baselines, especially in the few-shot regime. The approach is developed and deployed at Bayer, live since November 2021. As we believe our approach potentially promising beyond MC, and to ensure reproducibility, we release the code to the research community.
%R 10.18653/v1/2022.naacl-industry.21
%U https://aclanthology.org/2022.naacl-industry.21
%U https://doi.org/10.18653/v1/2022.naacl-industry.21
%P 176-187
Markdown (Informal)
[Medical Coding with Biomedical Transformer Ensembles and Zero/Few-shot Learning](https://aclanthology.org/2022.naacl-industry.21) (Ziletti et al., NAACL 2022)
ACL
- Angelo Ziletti, Alan Akbik, Christoph Berns, Thomas Herold, Marion Legler, and Martina Viell. 2022. Medical Coding with Biomedical Transformer Ensembles and Zero/Few-shot Learning. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track, pages 176–187, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.