Rethinking Skill Extraction in the Job Market Domain using Large Language Models

Khanh Cao Nguyen, Mike Zhang, Syrielle Montariol, Antoine Bosselut

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

Abstract

Skill Extraction involves identifying skills and qualifications mentioned in documents such as job postings and resumes. It 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 skill extraction datasets that we uniformize. 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.
OriginalsprogEngelsk
Titel1st Workshop on Natural Language Processing for Human Resources
Antal sider16
ForlagAssociation for Computational Linguistics
Publikationsdatomar. 2024
Sider27–42
StatusUdgivet - mar. 2024
BegivenhedNLP4HR WORKSHOP 2024: Workshop on Natural Language Processing for Human Resources - St. Julians, Malta
Varighed: 22 mar. 2024 → …
https://megagon.ai/nlp4hr-2024/

Workshop

WorkshopNLP4HR WORKSHOP 2024
Land/OmrådeMalta
BySt. Julians
Periode22/03/2024 → …
Internetadresse

Fingeraftryk

Dyk ned i forskningsemnerne om 'Rethinking Skill Extraction in the Job Market Domain using Large Language Models'. Sammen danner de et unikt fingeraftryk.

Citationsformater