Effectiveness of Domain Adaptation Approaches for Social Media PoS Tagging

Horsmann, Tobias; Zesch, Torsten

doi:10.4000/books.aaccademia.1494

Tagungsbeitrag 2015 CC BY-NC-ND 4.0

Veröffentlicht

Effectiveness of Domain Adaptation Approaches for Social Media PoS Tagging

We compare a comprehensive list of domain adaptation approaches for PoS tagging of social media data. We find that the most effective approach is based on clustering of unlabeled data. We also show that combining different approaches does not further improve performance. Thus, PoS tagging of social media data remains a challenging problem.

Vorschau

Einordnung

Konferenz:: Second Italian Conference on Computational Linguistics CLiC-it 2015, 3-4 December 2015, Trento
Datum der Veröffentlichung:: 2015
URN:: urn:nbn:de:hbz:464-20211022-122109-1
DOI:: 10.4000/books.aaccademia.1494
Sprache:: Englisch
Ressourcentyp:: Text
Kollektion:: E-Publikationen
Sachgruppen der Deutschen Nationalbibliographie:: 004 Informatik
Einrichtung:: Fakultät für Ingenieurwissenschaften, Informatik und Angewandte Kognitionswissenschaft, Informatik, Sprachtechnologie
Informationen zur Erstveröffentlichung:: Horsmann, T., & Zesch, T. (2015). Effectiveness of Domain Adaptation Approaches for Social Media PoS Tagging. In: Bosco, C., Tonelli, S., & Zanzotto, F. M. (Eds.) Proceedings of the Second Italian Conference on Computational Linguistics CLiC-it 2015 : 3-4 December 2015, Trento, pp. 166-170. Torino : Accademia University Press. doi: 10.4000/books.aaccademia.1494