Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-4875
Publication type: | Conference paper |
Type of review: | Peer review (publication) |
Title: | Syntactic manipulation for generating more diverse and interesting texts |
Authors: | Deriu, Jan Milan Cieliebak, Mark |
DOI: | 10.21256/zhaw-4875 |
Proceedings: | Proceedings of the 11th International Conference on Natural Language Generation |
Page(s): | 22 |
Pages to: | 34 |
Conference details: | 11th International Conference on Natural Language Generation (INLG 2018), Tilburg, The Netherlands, 5-8 November 2018 |
Issue Date: | 2018 |
Publisher / Ed. Institution: | Association for Computational Linguistics |
Language: | English |
Subjects: | Natural language generation; Natural language processing; Deep neural networks; Neural networks; Text embellishment |
Subject (DDC): | 006: Special computer methods 410.285: Computational linguistics |
Abstract: | 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 |
Fulltext version: | Published version |
License (according to publishing contract): | CC BY 4.0: Attribution 4.0 International |
Departement: | School of Engineering |
Organisational Unit: | Institute of Computer Science (InIT) |
Appears in collections: | Publikationen School of Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2018_Deriu_Syntactic_manipulation_for_generating_more_diverse_and_interesting_texts.pdf | 276.23 kB | Adobe PDF | View/Open |
Show full item record
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.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.