@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",
    editor = "Bamman, David  and
      Hovy, Dirk  and
      Jurgens, David  and
      O'Connor, Brendan  and
      Volkova, Svitlana",
    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://preview.aclanthology.org/fix-sig-urls/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."
}