@inproceedings{naguib-etal-2024-shot,
title = "Few-shot clinical entity recognition in {E}nglish, {F}rench and {S}panish: masked language models outperform generative model prompting",
author = "Naguib, Marco and
Tannier, Xavier and
N{\'e}v{\'e}ol, Aur{\'e}lie",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.400",
pages = "6829--6852",
abstract = "Large language models (LLMs) have become the preferred solution for many natural language processing tasks. In low-resource environments such as specialized domains, their few-shot capabilities are expected to deliver high performance. Named Entity Recognition (NER) is a critical task in information extraction that is not covered in recent LLM benchmarks. There is a need for better understanding the performance of LLMs for NER in a variety of settings including languages other than English. This study aims to evaluate generative LLMs, employed through prompt engineering, for few-shot clinical NER. We compare 13 auto-regressive models using prompting and 16 masked models using fine-tuning on 14 NER datasets covering English, French and Spanish. While prompt-based auto-regressive models achieve competitive F1 for general NER, they are outperformed within the clinical domain by lighter biLSTM-CRF taggers based on masked models. Additionally, masked models exhibit lower environmental impact compared to auto-regressive models. Findings are consistent across the three languages studied, which suggests that LLM prompting is not yet suited for NER production in the clinical domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="naguib-etal-2024-shot">
<titleInfo>
<title>Few-shot clinical entity recognition in English, French and Spanish: masked language models outperform generative model prompting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Naguib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xavier</namePart>
<namePart type="family">Tannier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurélie</namePart>
<namePart type="family">Névéol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) have become the preferred solution for many natural language processing tasks. In low-resource environments such as specialized domains, their few-shot capabilities are expected to deliver high performance. Named Entity Recognition (NER) is a critical task in information extraction that is not covered in recent LLM benchmarks. There is a need for better understanding the performance of LLMs for NER in a variety of settings including languages other than English. This study aims to evaluate generative LLMs, employed through prompt engineering, for few-shot clinical NER. We compare 13 auto-regressive models using prompting and 16 masked models using fine-tuning on 14 NER datasets covering English, French and Spanish. While prompt-based auto-regressive models achieve competitive F1 for general NER, they are outperformed within the clinical domain by lighter biLSTM-CRF taggers based on masked models. Additionally, masked models exhibit lower environmental impact compared to auto-regressive models. Findings are consistent across the three languages studied, which suggests that LLM prompting is not yet suited for NER production in the clinical domain.</abstract>
<identifier type="citekey">naguib-etal-2024-shot</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.400</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>6829</start>
<end>6852</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Few-shot clinical entity recognition in English, French and Spanish: masked language models outperform generative model prompting
%A Naguib, Marco
%A Tannier, Xavier
%A Névéol, Aurélie
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F naguib-etal-2024-shot
%X Large language models (LLMs) have become the preferred solution for many natural language processing tasks. In low-resource environments such as specialized domains, their few-shot capabilities are expected to deliver high performance. Named Entity Recognition (NER) is a critical task in information extraction that is not covered in recent LLM benchmarks. There is a need for better understanding the performance of LLMs for NER in a variety of settings including languages other than English. This study aims to evaluate generative LLMs, employed through prompt engineering, for few-shot clinical NER. We compare 13 auto-regressive models using prompting and 16 masked models using fine-tuning on 14 NER datasets covering English, French and Spanish. While prompt-based auto-regressive models achieve competitive F1 for general NER, they are outperformed within the clinical domain by lighter biLSTM-CRF taggers based on masked models. Additionally, masked models exhibit lower environmental impact compared to auto-regressive models. Findings are consistent across the three languages studied, which suggests that LLM prompting is not yet suited for NER production in the clinical domain.
%U https://aclanthology.org/2024.findings-emnlp.400
%P 6829-6852
Markdown (Informal)
[Few-shot clinical entity recognition in English, French and Spanish: masked language models outperform generative model prompting](https://aclanthology.org/2024.findings-emnlp.400) (Naguib et al., Findings 2024)
ACL