@inproceedings{berkowitz-etal-2024-tlab,
title = "{TL}ab at {\#}{SMM}4{H} 2024: Retrieval-Augmented Generation for {ADE} Extraction and Normalization",
author = "Berkowitz, Jacob and
Srinivasan, Apoorva and
Cortina, Jose and
Tatonetti1, Nicholas",
editor = "Xu, Dongfang and
Gonzalez-Hernandez, Graciela",
booktitle = "Proceedings of The 9th Social Media Mining for Health Research and Applications (SMM4H 2024) Workshop and Shared Tasks",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.smm4h-1.36",
pages = "153--157",
abstract = "SMM4H 2024 Task 1 is focused on the identification of standardized Adverse Drug Events (ADEs) in tweets. We introduce a novel Retrieval-Augmented Generation (RAG) method, leveraging the capabilities of Llama 3, GPT-4, and the SFR-embedding-mistral model, along with few-shot prompting techniques, to map colloquial tweet language to MedDRA Preferred Terms (PTs) without relying on extensive training datasets. Our method achieved competitive performance, with an F1 score of 0.359 in the normalization task and 0.392 in the named entity recognition (NER) task. Notably, our model demonstrated robustness in identifying previously unseen MedDRA PTs (F1=0.363) greatly surpassing the median task score of 0.141 for such terms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="berkowitz-etal-2024-tlab">
<titleInfo>
<title>TLab at #SMM4H 2024: Retrieval-Augmented Generation for ADE Extraction and Normalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Berkowitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apoorva</namePart>
<namePart type="family">Srinivasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Cortina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Tatonetti1</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The 9th Social Media Mining for Health Research and Applications (SMM4H 2024) Workshop and Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongfang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>SMM4H 2024 Task 1 is focused on the identification of standardized Adverse Drug Events (ADEs) in tweets. We introduce a novel Retrieval-Augmented Generation (RAG) method, leveraging the capabilities of Llama 3, GPT-4, and the SFR-embedding-mistral model, along with few-shot prompting techniques, to map colloquial tweet language to MedDRA Preferred Terms (PTs) without relying on extensive training datasets. Our method achieved competitive performance, with an F1 score of 0.359 in the normalization task and 0.392 in the named entity recognition (NER) task. Notably, our model demonstrated robustness in identifying previously unseen MedDRA PTs (F1=0.363) greatly surpassing the median task score of 0.141 for such terms.</abstract>
<identifier type="citekey">berkowitz-etal-2024-tlab</identifier>
<location>
<url>https://aclanthology.org/2024.smm4h-1.36</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>153</start>
<end>157</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TLab at #SMM4H 2024: Retrieval-Augmented Generation for ADE Extraction and Normalization
%A Berkowitz, Jacob
%A Srinivasan, Apoorva
%A Cortina, Jose
%A Tatonetti1, Nicholas
%Y Xu, Dongfang
%Y Gonzalez-Hernandez, Graciela
%S Proceedings of The 9th Social Media Mining for Health Research and Applications (SMM4H 2024) Workshop and Shared Tasks
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F berkowitz-etal-2024-tlab
%X SMM4H 2024 Task 1 is focused on the identification of standardized Adverse Drug Events (ADEs) in tweets. We introduce a novel Retrieval-Augmented Generation (RAG) method, leveraging the capabilities of Llama 3, GPT-4, and the SFR-embedding-mistral model, along with few-shot prompting techniques, to map colloquial tweet language to MedDRA Preferred Terms (PTs) without relying on extensive training datasets. Our method achieved competitive performance, with an F1 score of 0.359 in the normalization task and 0.392 in the named entity recognition (NER) task. Notably, our model demonstrated robustness in identifying previously unseen MedDRA PTs (F1=0.363) greatly surpassing the median task score of 0.141 for such terms.
%U https://aclanthology.org/2024.smm4h-1.36
%P 153-157
Markdown (Informal)
[TLab at #SMM4H 2024: Retrieval-Augmented Generation for ADE Extraction and Normalization](https://aclanthology.org/2024.smm4h-1.36) (Berkowitz et al., SMM4H-WS 2024)
ACL