@inproceedings{nguyen-etal-2024-rethinking,
title = "Rethinking Skill Extraction in the Job Market Domain using Large Language Models",
author = "Nguyen, Khanh and
Zhang, Mike and
Montariol, Syrielle and
Bosselut, Antoine",
editor = "Hruschka, Estevam and
Lake, Thom and
Otani, Naoki and
Mitchell, Tom",
booktitle = "Proceedings of the First Workshop on Natural Language Processing for Human Resources (NLP4HR 2024)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nlp4hr-1.3",
pages = "27--42",
abstract = "Skill Extraction involves identifying skills and qualifications mentioned in documents such as job postings and resumes. The task is commonly tackled by training supervised models using a sequence labeling approach with BIO tags. However, the reliance on manually annotated data limits the generalizability of such approaches. Moreover, the common BIO setting limits the ability of the models to capture complex skill patterns and handle ambiguous mentions. In this paper, we explore the use of in-context learning to overcome these challenges, on a benchmark of 6 uniformized skill extraction datasets. Our approach leverages the few-shot learning capabilities of large language models (LLMs) to identify and extract skills from sentences. We show that LLMs, despite not being on par with traditional supervised models in terms of performance, can better handle syntactically complex skill mentions in skill extraction tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2024-rethinking">
<titleInfo>
<title>Rethinking Skill Extraction in the Job Market Domain using Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khanh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syrielle</namePart>
<namePart type="family">Montariol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Natural Language Processing for Human Resources (NLP4HR 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Estevam</namePart>
<namePart type="family">Hruschka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thom</namePart>
<namePart type="family">Lake</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoki</namePart>
<namePart type="family">Otani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Mitchell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Skill Extraction involves identifying skills and qualifications mentioned in documents such as job postings and resumes. The task is commonly tackled by training supervised models using a sequence labeling approach with BIO tags. However, the reliance on manually annotated data limits the generalizability of such approaches. Moreover, the common BIO setting limits the ability of the models to capture complex skill patterns and handle ambiguous mentions. In this paper, we explore the use of in-context learning to overcome these challenges, on a benchmark of 6 uniformized skill extraction datasets. Our approach leverages the few-shot learning capabilities of large language models (LLMs) to identify and extract skills from sentences. We show that LLMs, despite not being on par with traditional supervised models in terms of performance, can better handle syntactically complex skill mentions in skill extraction tasks.</abstract>
<identifier type="citekey">nguyen-etal-2024-rethinking</identifier>
<location>
<url>https://aclanthology.org/2024.nlp4hr-1.3</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>27</start>
<end>42</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rethinking Skill Extraction in the Job Market Domain using Large Language Models
%A Nguyen, Khanh
%A Zhang, Mike
%A Montariol, Syrielle
%A Bosselut, Antoine
%Y Hruschka, Estevam
%Y Lake, Thom
%Y Otani, Naoki
%Y Mitchell, Tom
%S Proceedings of the First Workshop on Natural Language Processing for Human Resources (NLP4HR 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F nguyen-etal-2024-rethinking
%X Skill Extraction involves identifying skills and qualifications mentioned in documents such as job postings and resumes. The task is commonly tackled by training supervised models using a sequence labeling approach with BIO tags. However, the reliance on manually annotated data limits the generalizability of such approaches. Moreover, the common BIO setting limits the ability of the models to capture complex skill patterns and handle ambiguous mentions. In this paper, we explore the use of in-context learning to overcome these challenges, on a benchmark of 6 uniformized skill extraction datasets. Our approach leverages the few-shot learning capabilities of large language models (LLMs) to identify and extract skills from sentences. We show that LLMs, despite not being on par with traditional supervised models in terms of performance, can better handle syntactically complex skill mentions in skill extraction tasks.
%U https://aclanthology.org/2024.nlp4hr-1.3
%P 27-42
Markdown (Informal)
[Rethinking Skill Extraction in the Job Market Domain using Large Language Models](https://aclanthology.org/2024.nlp4hr-1.3) (Nguyen et al., NLP4HR-WS 2024)
ACL