@inproceedings{gnehm-etal-2022-evaluation,
title = "Evaluation of Transfer Learning and Domain Adaptation for Analyzing {G}erman-Speaking Job Advertisements",
author = {Gnehm, Ann-Sophie and
B{\"u}hlmann, Eva and
Clematide, Simon},
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.414/",
pages = "3892--3901",
abstract = "This paper presents text mining approaches on German-speaking job advertisements to enable social science research on the development of the labour market over the last 30 years. In order to build text mining applications providing information about profession and main task of a job, as well as experience and ICT skills needed, we experiment with transfer learning and domain adaptation. Our main contribution consists in building language models which are adapted to the domain of job advertisements, and their assessment on a broad range of machine learning problems. Our findings show the large value of domain adaptation in several respects. First, it boosts the performance of fine-tuned task-specific models consistently over all evaluation experiments. Second, it helps to mitigate rapid data shift over time in our special domain, and enhances the ability to learn from small updates with new, labeled task data. Third, domain-adaptation of language models is efficient: With continued in-domain pre-training we are able to outperform general-domain language models pre-trained on ten times more data. We share our domain-adapted language models and data with the research community."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gnehm-etal-2022-evaluation">
<titleInfo>
<title>Evaluation of Transfer Learning and Domain Adaptation for Analyzing German-Speaking Job Advertisements</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ann-Sophie</namePart>
<namePart type="family">Gnehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Bühlmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Clematide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents text mining approaches on German-speaking job advertisements to enable social science research on the development of the labour market over the last 30 years. In order to build text mining applications providing information about profession and main task of a job, as well as experience and ICT skills needed, we experiment with transfer learning and domain adaptation. Our main contribution consists in building language models which are adapted to the domain of job advertisements, and their assessment on a broad range of machine learning problems. Our findings show the large value of domain adaptation in several respects. First, it boosts the performance of fine-tuned task-specific models consistently over all evaluation experiments. Second, it helps to mitigate rapid data shift over time in our special domain, and enhances the ability to learn from small updates with new, labeled task data. Third, domain-adaptation of language models is efficient: With continued in-domain pre-training we are able to outperform general-domain language models pre-trained on ten times more data. We share our domain-adapted language models and data with the research community.</abstract>
<identifier type="citekey">gnehm-etal-2022-evaluation</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.414/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3892</start>
<end>3901</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluation of Transfer Learning and Domain Adaptation for Analyzing German-Speaking Job Advertisements
%A Gnehm, Ann-Sophie
%A Bühlmann, Eva
%A Clematide, Simon
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F gnehm-etal-2022-evaluation
%X This paper presents text mining approaches on German-speaking job advertisements to enable social science research on the development of the labour market over the last 30 years. In order to build text mining applications providing information about profession and main task of a job, as well as experience and ICT skills needed, we experiment with transfer learning and domain adaptation. Our main contribution consists in building language models which are adapted to the domain of job advertisements, and their assessment on a broad range of machine learning problems. Our findings show the large value of domain adaptation in several respects. First, it boosts the performance of fine-tuned task-specific models consistently over all evaluation experiments. Second, it helps to mitigate rapid data shift over time in our special domain, and enhances the ability to learn from small updates with new, labeled task data. Third, domain-adaptation of language models is efficient: With continued in-domain pre-training we are able to outperform general-domain language models pre-trained on ten times more data. We share our domain-adapted language models and data with the research community.
%U https://aclanthology.org/2022.lrec-1.414/
%P 3892-3901
Markdown (Informal)
[Evaluation of Transfer Learning and Domain Adaptation for Analyzing German-Speaking Job Advertisements](https://aclanthology.org/2022.lrec-1.414/) (Gnehm et al., LREC 2022)
ACL