@inproceedings{de-santo-etal-2026-skillens,
title = "{S}ki{LL}ens: Recognising and Mapping Novel Skills from Millions of Job Ads Across {E}urope Using Language Models",
author = "De Santo, Alessia and
Malandri, Lorenzo and
Mercorio, Fabio and
Mezzanzanica, Mario and
Nobani, Navid",
editor = {Matusevych, Yevgen and
Eryi{\u{g}}it, G{\"u}l{\c{s}}en and
Aletras, Nikolaos},
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 5: Industry Track)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-industry.65/",
pages = "877--885",
ISBN = "979-8-89176-384-5",
abstract = "In a rapidly evolving labor market, detecting and addressing emerging skill needs is essential for shaping responsive education and workforce policies. Online job advertisements (OJAs) provide a real-time view of changing demands, but require first retrieving skill mentions from unstructured text and then solving the entity linking problem of connecting them to standardized skill taxonomies. To harness this potential, we present a multilingual human-in-the-loop (HITL) pipeline that operates in two steps: candidate skills are extracted from national OJA corpora using country-specific word embeddings, capturing terms that reflect each country{'}s labor market. These candidates are linked to ESCO using an encoder-based system and refined through a decoder large language models (LLMs) for accurate contextual alignment. Our approach is validated through both quantitative and qualitative evaluations, demonstrating that our method enables timely, multilingual monitoring of emerging skills, supporting agile policy-making and targeted training initiatives."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-santo-etal-2026-skillens">
<titleInfo>
<title>SkiLLens: Recognising and Mapping Novel Skills from Millions of Job Ads Across Europe Using Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alessia</namePart>
<namePart type="family">De Santo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lorenzo</namePart>
<namePart type="family">Malandri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Mercorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Mezzanzanica</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Navid</namePart>
<namePart type="family">Nobani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yevgen</namePart>
<namePart type="family">Matusevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gülşen</namePart>
<namePart type="family">Eryiğit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-384-5</identifier>
</relatedItem>
<abstract>In a rapidly evolving labor market, detecting and addressing emerging skill needs is essential for shaping responsive education and workforce policies. Online job advertisements (OJAs) provide a real-time view of changing demands, but require first retrieving skill mentions from unstructured text and then solving the entity linking problem of connecting them to standardized skill taxonomies. To harness this potential, we present a multilingual human-in-the-loop (HITL) pipeline that operates in two steps: candidate skills are extracted from national OJA corpora using country-specific word embeddings, capturing terms that reflect each country’s labor market. These candidates are linked to ESCO using an encoder-based system and refined through a decoder large language models (LLMs) for accurate contextual alignment. Our approach is validated through both quantitative and qualitative evaluations, demonstrating that our method enables timely, multilingual monitoring of emerging skills, supporting agile policy-making and targeted training initiatives.</abstract>
<identifier type="citekey">de-santo-etal-2026-skillens</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-industry.65/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>877</start>
<end>885</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SkiLLens: Recognising and Mapping Novel Skills from Millions of Job Ads Across Europe Using Language Models
%A De Santo, Alessia
%A Malandri, Lorenzo
%A Mercorio, Fabio
%A Mezzanzanica, Mario
%A Nobani, Navid
%Y Matusevych, Yevgen
%Y Eryiğit, Gülşen
%Y Aletras, Nikolaos
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-384-5
%F de-santo-etal-2026-skillens
%X In a rapidly evolving labor market, detecting and addressing emerging skill needs is essential for shaping responsive education and workforce policies. Online job advertisements (OJAs) provide a real-time view of changing demands, but require first retrieving skill mentions from unstructured text and then solving the entity linking problem of connecting them to standardized skill taxonomies. To harness this potential, we present a multilingual human-in-the-loop (HITL) pipeline that operates in two steps: candidate skills are extracted from national OJA corpora using country-specific word embeddings, capturing terms that reflect each country’s labor market. These candidates are linked to ESCO using an encoder-based system and refined through a decoder large language models (LLMs) for accurate contextual alignment. Our approach is validated through both quantitative and qualitative evaluations, demonstrating that our method enables timely, multilingual monitoring of emerging skills, supporting agile policy-making and targeted training initiatives.
%U https://aclanthology.org/2026.eacl-industry.65/
%P 877-885
Markdown (Informal)
[SkiLLens: Recognising and Mapping Novel Skills from Millions of Job Ads Across Europe Using Language Models](https://aclanthology.org/2026.eacl-industry.65/) (De Santo et al., EACL 2026)
ACL