Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
https://doi.org/10.21256/zhaw-1531| Publikationstyp: | Konferenz: Paper |
| Art der Begutachtung: | Peer review (Publikation) |
| Titel: | Author profiling with bidirectional RNNs using attention with GRUs : notebook for PAN at CLEF 2017 |
| Autor/-in: | Kodiyan, Don Hardegger, Florin Neuhaus, Stephan Cieliebak, Mark |
| DOI: | 10.21256/zhaw-1531 |
| Tagungsband: | CLEF 2017 Evaluation Labs and Workshop – Working Notes Papers |
| Band(Heft): | 1866 |
| Angaben zur Konferenz: | CLEF 2017 Conference and Labs of the Evaluation Forum, Dublin, Ireland, 11-14 September 2017 |
| Erscheinungsdatum: | 2017 |
| Verlag / Hrsg. Institution: | RWTH Aachen |
| ISSN: | 1613-0073 |
| Sprache: | Englisch |
| Schlagwörter: | Gender Classification; Author Profiling |
| Fachgebiet (DDC): | 006: Spezielle Computerverfahren |
| Zusammenfassung: | This paper describes our approach for the Author Profiling Shared Task at PAN 2017. The goal was to classify the gender and language variety of a Twitter user solely by their tweets. Author Profiling can be applied in various fields like marketing, security and forensics. Twitter already uses similar techniques to deliver personalized advertisement for their users. PAN 2017 provided a corpus for this purpose in the languages: English, Spanish, Portuguese and Arabic. To solve the problem we used a deep learning approach, which has shown recent success in Natural Language Processing. Our submitted model consists of a bidirectional Recurrent Neural Network implemented with a Gated Recurrent Unit (GRU) combined with an Attention Mechanism. We achieved an average accuracy over all languages of 75,31% in gender classification and 85,22% in language variety classification. |
| URI: | https://digitalcollection.zhaw.ch/handle/11475/1865 |
| Volltext Version: | Publizierte Version |
| Lizenz (gemäss Verlagsvertrag): | Lizenz gemäss Verlagsvertrag |
| Departement: | School of Engineering |
| Organisationseinheit: | Institut für Informatik (InIT) |
| Enthalten in den Sammlungen: | Publikationen School of Engineering |
Dateien zu dieser Ressource:
| Datei | Beschreibung | Größe | Format | |
|---|---|---|---|---|
| kodiyan17-notebook.pdf | 361.5 kB | Adobe PDF |  Öffnen/Anzeigen |
Zur Langanzeige
Kodiyan, D., Hardegger, F., Neuhaus, S., & Cieliebak, M. (2017). Author profiling with bidirectional RNNs using attention with GRUs : notebook for PAN at CLEF 2017 [Conference paper]. CLEF 2017 Evaluation Labs and Workshop – Working Notes Papers, 1866. https://doi.org/10.21256/zhaw-1531
Kodiyan, D. et al. (2017) ‘Author profiling with bidirectional RNNs using attention with GRUs : notebook for PAN at CLEF 2017’, in CLEF 2017 Evaluation Labs and Workshop – Working Notes Papers. RWTH Aachen. Available at: https://doi.org/10.21256/zhaw-1531.
D. Kodiyan, F. Hardegger, S. Neuhaus, and M. Cieliebak, “Author profiling with bidirectional RNNs using attention with GRUs : notebook for PAN at CLEF 2017,” in CLEF 2017 Evaluation Labs and Workshop – Working Notes Papers, 2017, vol. 1866. doi: 10.21256/zhaw-1531.
KODIYAN, Don, Florin HARDEGGER, Stephan NEUHAUS und Mark CIELIEBAK, 2017. Author profiling with bidirectional RNNs using attention with GRUs : notebook for PAN at CLEF 2017. In: CLEF 2017 Evaluation Labs and Workshop – Working Notes Papers. Conference paper. RWTH Aachen. 2017
Kodiyan, Don, Florin Hardegger, Stephan Neuhaus, and Mark Cieliebak. 2017. “Author Profiling with Bidirectional RNNs Using Attention with GRUs : Notebook for PAN at CLEF 2017.” Conference paper. In CLEF 2017 Evaluation Labs and Workshop – Working Notes Papers. Vol. 1866. RWTH Aachen. https://doi.org/10.21256/zhaw-1531.
Kodiyan, Don, et al. “Author Profiling with Bidirectional RNNs Using Attention with GRUs : Notebook for PAN at CLEF 2017.” CLEF 2017 Evaluation Labs and Workshop – Working Notes Papers, vol. 1866, RWTH Aachen, 2017, https://doi.org/10.21256/zhaw-1531.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.