Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
https://doi.org/10.21256/zhaw-4850
Publikationstyp: | Konferenz: Paper |
Art der Begutachtung: | Peer review (Publikation) |
Titel: | Twist Bytes : German dialect identification with data mining optimization |
Autor/-in: | Benites de Azevedo e Souza, Fernando Grubenmann, Ralf von Däniken, Pius von Grünigen, Dirk Deriu, Jan Milan Cieliebak, Mark |
DOI: | 10.21256/zhaw-4850 |
Tagungsband: | Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018) |
Seite(n): | 218 |
Seiten bis: | 227 |
Angaben zur Konferenz: | 27th International Conference on Computational Linguistics (COLING 2018), Santa Fe, August 20-26, 2018 |
Erscheinungsdatum: | 2018 |
Verlag / Hrsg. Institution: | VarDial |
Sprache: | Englisch |
Schlagwörter: | Dialect recognition; Text classification; Shared task; Swiss german |
Fachgebiet (DDC): | 410.285: Computerlinguistik 430: Deutsch |
Zusammenfassung: | We describe our approaches used in the German Dialect Identification (GDI) task at the VarDial Evaluation Campaign 2018. The goal was to identify to which out of four dialects spoken in German speaking part of Switzerland a sentence belonged to. We adopted two different metaclassifier approaches and used some data mining insights to improve the preprocessing and the meta-classifier parameters. Especially, we focused on using different feature extraction methods and how to combine them, since they influenced the performance very differently of the system. Our system achieved second place out of 8 teams, with a macro averaged F-1 of 64.6%. We also participated on the surprise dialect task with a multi-label approach. |
URI: | http://www.aclweb.org/anthology/W18-3925 https://digitalcollection.zhaw.ch/handle/11475/11222 |
Volltext Version: | Publizierte Version |
Lizenz (gemäss Verlagsvertrag): | CC BY 4.0: Namensnennung 4.0 International |
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 | |
---|---|---|---|---|
2018_Benites_Twist_Bytes_German_Dialect_Identification_with_data_mining_optimization.pdf | 250.32 kB | Adobe PDF | Öffnen/Anzeigen |
Zur Langanzeige
Benites de Azevedo e Souza, F., Grubenmann, R., von Däniken, P., von Grünigen, D., Deriu, J. M., & Cieliebak, M. (2018). Twist Bytes : German dialect identification with data mining optimization [Conference paper]. Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018), 218–227. https://doi.org/10.21256/zhaw-4850
Benites de Azevedo e Souza, F. et al. (2018) ‘Twist Bytes : German dialect identification with data mining optimization’, in Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018). VarDial, pp. 218–227. Available at: https://doi.org/10.21256/zhaw-4850.
F. Benites de Azevedo e Souza, R. Grubenmann, P. von Däniken, D. von Grünigen, J. M. Deriu, and M. Cieliebak, “Twist Bytes : German dialect identification with data mining optimization,” in Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018), 2018, pp. 218–227. doi: 10.21256/zhaw-4850.
BENITES DE AZEVEDO E SOUZA, Fernando, Ralf GRUBENMANN, Pius VON DÄNIKEN, Dirk VON GRÜNIGEN, Jan Milan DERIU und Mark CIELIEBAK, 2018. Twist Bytes : German dialect identification with data mining optimization. In: Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018) [online]. Conference paper. VarDial. 2018. S. 218–227. Verfügbar unter: http://www.aclweb.org/anthology/W18-3925
Benites de Azevedo e Souza, Fernando, Ralf Grubenmann, Pius von Däniken, Dirk von Grünigen, Jan Milan Deriu, and Mark Cieliebak. 2018. “Twist Bytes : German Dialect Identification with Data Mining Optimization.” Conference paper. In Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018), 218–27. VarDial. https://doi.org/10.21256/zhaw-4850.
Benites de Azevedo e Souza, Fernando, et al. “Twist Bytes : German Dialect Identification with Data Mining Optimization.” Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018), VarDial, 2018, pp. 218–27, https://doi.org/10.21256/zhaw-4850.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.