Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
https://doi.org/10.21256/zhaw-4875
Publikationstyp: | Konferenz: Paper |
Art der Begutachtung: | Peer review (Publikation) |
Titel: | Syntactic manipulation for generating more diverse and interesting texts |
Autor/-in: | Deriu, Jan Milan Cieliebak, Mark |
DOI: | 10.21256/zhaw-4875 |
Tagungsband: | Proceedings of the 11th International Conference on Natural Language Generation |
Seite(n): | 22 |
Seiten bis: | 34 |
Angaben zur Konferenz: | 11th International Conference on Natural Language Generation (INLG 2018), Tilburg, The Netherlands, 5-8 November 2018 |
Erscheinungsdatum: | 2018 |
Verlag / Hrsg. Institution: | Association for Computational Linguistics |
Sprache: | Englisch |
Schlagwörter: | Natural language generation; Natural language processing; Deep neural networks; Neural networks; Text embellishment |
Fachgebiet (DDC): | 006: Spezielle Computerverfahren 410.285: Computerlinguistik |
Zusammenfassung: | Natural Language Generation plays an important role in the domain of dialogue systems as it determines how users perceive the system. Recently, deep-learning based systems have been proposed to tackle this task, as they generalize better and require less amounts of manual effort to implement them for new domains. However, deep learning systems usually adapt a very homogeneous sounding writing style which expresses little variation. In this work, we present our system for Natural Language Generation where we control various aspects of the surface realization in order to increase the lexical variability of the utterances, such that they sound more diverse and interesting. For this, we use a Semantically Controlled Long Short-term Memory Network (SCLSTM), and apply its specialized cell to control various syntactic features of the generated texts. We present an in-depth human evaluation where we show the effects of these surface manipulation on the perception of potential users. |
URI: | http://aclweb.org/anthology/W18-6503 https://digitalcollection.zhaw.ch/handle/11475/13074 |
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_Deriu_Syntactic_manipulation_for_generating_more_diverse_and_interesting_texts.pdf | 276.23 kB | Adobe PDF | Öffnen/Anzeigen |
Zur Langanzeige
Deriu, J. M., & Cieliebak, M. (2018). Syntactic manipulation for generating more diverse and interesting texts [Conference paper]. Proceedings of the 11th International Conference on Natural Language Generation, 22–34. https://doi.org/10.21256/zhaw-4875
Deriu, J.M. and Cieliebak, M. (2018) ‘Syntactic manipulation for generating more diverse and interesting texts’, in Proceedings of the 11th International Conference on Natural Language Generation. Association for Computational Linguistics, pp. 22–34. Available at: https://doi.org/10.21256/zhaw-4875.
J. M. Deriu and M. Cieliebak, “Syntactic manipulation for generating more diverse and interesting texts,” in Proceedings of the 11th International Conference on Natural Language Generation, 2018, pp. 22–34. doi: 10.21256/zhaw-4875.
DERIU, Jan Milan und Mark CIELIEBAK, 2018. Syntactic manipulation for generating more diverse and interesting texts. In: Proceedings of the 11th International Conference on Natural Language Generation [online]. Conference paper. Association for Computational Linguistics. 2018. S. 22–34. Verfügbar unter: http://aclweb.org/anthology/W18-6503
Deriu, Jan Milan, and Mark Cieliebak. 2018. “Syntactic Manipulation for Generating More Diverse and Interesting Texts.” Conference paper. In Proceedings of the 11th International Conference on Natural Language Generation, 22–34. Association for Computational Linguistics. https://doi.org/10.21256/zhaw-4875.
Deriu, Jan Milan, and Mark Cieliebak. “Syntactic Manipulation for Generating More Diverse and Interesting Texts.” Proceedings of the 11th International Conference on Natural Language Generation, Association for Computational Linguistics, 2018, pp. 22–34, https://doi.org/10.21256/zhaw-4875.
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.