Syntactic Manipulation for Generating more Diverse and Interesting Texts

Jan Milan Deriu, Mark Cieliebak


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 (SC-LSTM), 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.
Anthology ID:
W18-6503
Volume:
Proceedings of the 11th International Conference on Natural Language Generation
Month:
November
Year:
2018
Address:
Tilburg University, The Netherlands
Editors:
Emiel Krahmer, Albert Gatt, Martijn Goudbeek
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
22–34
Language:
URL:
https://aclanthology.org/W18-6503
DOI:
10.18653/v1/W18-6503
Bibkey:
Cite (ACL):
Jan Milan Deriu and Mark Cieliebak. 2018. Syntactic Manipulation for Generating more Diverse and Interesting Texts. In Proceedings of the 11th International Conference on Natural Language Generation, pages 22–34, Tilburg University, The Netherlands. Association for Computational Linguistics.
Cite (Informal):
Syntactic Manipulation for Generating more Diverse and Interesting Texts (Deriu & Cieliebak, INLG 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6503.pdf
Code
 jderiu/e2e_nlg