@inproceedings{gnehm-clematide-2020-text,
title = "Text Zoning and Classification for Job Advertisements in {G}erman, {F}rench and {E}nglish",
author = "Gnehm, Ann-Sophie and
Clematide, Simon",
booktitle = "Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlpcss-1.10",
doi = "10.18653/v1/2020.nlpcss-1.10",
pages = "83--93",
abstract = "We present experiments to structure job ads into text zones and classify them into pro- fessions, industries and management functions, thereby facilitating social science analyses on labor marked demand. Our main contribution are empirical findings on the benefits of contextualized embeddings and the potential of multi-task models for this purpose. With contextualized in-domain embeddings in BiLSTM-CRF models, we reach an accuracy of 91{\%} for token-level text zoning and outperform previous approaches. A multi-tasking BERT model performs well for our classification tasks. We further compare transfer approaches for our multilingual data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gnehm-clematide-2020-text">
<titleInfo>
<title>Text Zoning and Classification for Job Advertisements in German, French and English</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">Simon</namePart>
<namePart type="family">Clematide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present experiments to structure job ads into text zones and classify them into pro- fessions, industries and management functions, thereby facilitating social science analyses on labor marked demand. Our main contribution are empirical findings on the benefits of contextualized embeddings and the potential of multi-task models for this purpose. With contextualized in-domain embeddings in BiLSTM-CRF models, we reach an accuracy of 91% for token-level text zoning and outperform previous approaches. A multi-tasking BERT model performs well for our classification tasks. We further compare transfer approaches for our multilingual data.</abstract>
<identifier type="citekey">gnehm-clematide-2020-text</identifier>
<identifier type="doi">10.18653/v1/2020.nlpcss-1.10</identifier>
<location>
<url>https://aclanthology.org/2020.nlpcss-1.10</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>83</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text Zoning and Classification for Job Advertisements in German, French and English
%A Gnehm, Ann-Sophie
%A Clematide, Simon
%S Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F gnehm-clematide-2020-text
%X We present experiments to structure job ads into text zones and classify them into pro- fessions, industries and management functions, thereby facilitating social science analyses on labor marked demand. Our main contribution are empirical findings on the benefits of contextualized embeddings and the potential of multi-task models for this purpose. With contextualized in-domain embeddings in BiLSTM-CRF models, we reach an accuracy of 91% for token-level text zoning and outperform previous approaches. A multi-tasking BERT model performs well for our classification tasks. We further compare transfer approaches for our multilingual data.
%R 10.18653/v1/2020.nlpcss-1.10
%U https://aclanthology.org/2020.nlpcss-1.10
%U https://doi.org/10.18653/v1/2020.nlpcss-1.10
%P 83-93
Markdown (Informal)
[Text Zoning and Classification for Job Advertisements in German, French and English](https://aclanthology.org/2020.nlpcss-1.10) (Gnehm & Clematide, NLP+CSS 2020)
ACL