@inproceedings{rajwal-etal-2024-em,
title = "{EM}{\_}{M}ixers at {MEDIQA}-{CORR} 2024: Knowledge-Enhanced Few-Shot In-Context Learning for Medical Error Detection and Correction",
author = "Rajwal, Swati and
Agichtein, Eugene and
Sarker, Abeed",
editor = "Naumann, Tristan and
Ben Abacha, Asma and
Bethard, Steven and
Roberts, Kirk and
Bitterman, Danielle",
booktitle = "Proceedings of the 6th Clinical Natural Language Processing Workshop",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.clinicalnlp-1.56",
doi = "10.18653/v1/2024.clinicalnlp-1.56",
pages = "590--595",
abstract = "This paper describes our submission to MEDIQA-CORR 2024 shared task for automatic identification and correction of medical errors in a given clinical text. We report results from two approaches: the first uses a few-shot in-context learning (ICL) with a Large Language Model (LLM) and the second approach extends the idea by using a knowledge-enhanced few-shot ICL approach. We used Azure OpenAI GPT-4 API as the LLM and Wikipedia as the external knowledge source. We report evaluation metrics (accuracy, ROUGE, BERTScore, BLEURT) across both approaches for validation and test datasets. Of the two approaches implemented, our experimental results show that the knowledge-enhanced few-shot ICL approach with GPT-4 performed better with error flag (subtask A) and error sentence detection (subtask B) with accuracies of 68{\%} and 64{\%}, respectively on the test dataset. These results positioned us fourth in subtask A and second in subtask B, respectively in the shared task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajwal-etal-2024-em">
<titleInfo>
<title>EM_Mixers at MEDIQA-CORR 2024: Knowledge-Enhanced Few-Shot In-Context Learning for Medical Error Detection and Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Swati</namePart>
<namePart type="family">Rajwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugene</namePart>
<namePart type="family">Agichtein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abeed</namePart>
<namePart type="family">Sarker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our submission to MEDIQA-CORR 2024 shared task for automatic identification and correction of medical errors in a given clinical text. We report results from two approaches: the first uses a few-shot in-context learning (ICL) with a Large Language Model (LLM) and the second approach extends the idea by using a knowledge-enhanced few-shot ICL approach. We used Azure OpenAI GPT-4 API as the LLM and Wikipedia as the external knowledge source. We report evaluation metrics (accuracy, ROUGE, BERTScore, BLEURT) across both approaches for validation and test datasets. Of the two approaches implemented, our experimental results show that the knowledge-enhanced few-shot ICL approach with GPT-4 performed better with error flag (subtask A) and error sentence detection (subtask B) with accuracies of 68% and 64%, respectively on the test dataset. These results positioned us fourth in subtask A and second in subtask B, respectively in the shared task.</abstract>
<identifier type="citekey">rajwal-etal-2024-em</identifier>
<identifier type="doi">10.18653/v1/2024.clinicalnlp-1.56</identifier>
<location>
<url>https://aclanthology.org/2024.clinicalnlp-1.56</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>590</start>
<end>595</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EM_Mixers at MEDIQA-CORR 2024: Knowledge-Enhanced Few-Shot In-Context Learning for Medical Error Detection and Correction
%A Rajwal, Swati
%A Agichtein, Eugene
%A Sarker, Abeed
%Y Naumann, Tristan
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Bitterman, Danielle
%S Proceedings of the 6th Clinical Natural Language Processing Workshop
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F rajwal-etal-2024-em
%X This paper describes our submission to MEDIQA-CORR 2024 shared task for automatic identification and correction of medical errors in a given clinical text. We report results from two approaches: the first uses a few-shot in-context learning (ICL) with a Large Language Model (LLM) and the second approach extends the idea by using a knowledge-enhanced few-shot ICL approach. We used Azure OpenAI GPT-4 API as the LLM and Wikipedia as the external knowledge source. We report evaluation metrics (accuracy, ROUGE, BERTScore, BLEURT) across both approaches for validation and test datasets. Of the two approaches implemented, our experimental results show that the knowledge-enhanced few-shot ICL approach with GPT-4 performed better with error flag (subtask A) and error sentence detection (subtask B) with accuracies of 68% and 64%, respectively on the test dataset. These results positioned us fourth in subtask A and second in subtask B, respectively in the shared task.
%R 10.18653/v1/2024.clinicalnlp-1.56
%U https://aclanthology.org/2024.clinicalnlp-1.56
%U https://doi.org/10.18653/v1/2024.clinicalnlp-1.56
%P 590-595
Markdown (Informal)
[EM_Mixers at MEDIQA-CORR 2024: Knowledge-Enhanced Few-Shot In-Context Learning for Medical Error Detection and Correction](https://aclanthology.org/2024.clinicalnlp-1.56) (Rajwal et al., ClinicalNLP-WS 2024)
ACL