Controlling Linguistic Style Aspects in Neural Language Generation

Jessica Ficler, Yoav Goldberg


Abstract
Most work on neural natural language generation (NNLG) focus on controlling the content of the generated text. We experiment with controling several stylistic aspects of the generated text, in addition to its content. The method is based on conditioned RNN language model, where the desired content as well as the stylistic parameters serve as conditioning contexts. We demonstrate the approach on the movie reviews domain and show that it is successful in generating coherent sentences corresponding to the required linguistic style and content.
Anthology ID:
W17-4912
Volume:
Proceedings of the Workshop on Stylistic Variation
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Julian Brooke, Thamar Solorio, Moshe Koppel
Venue:
Style-Var
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
94–104
Language:
URL:
https://aclanthology.org/W17-4912
DOI:
10.18653/v1/W17-4912
Bibkey:
Cite (ACL):
Jessica Ficler and Yoav Goldberg. 2017. Controlling Linguistic Style Aspects in Neural Language Generation. In Proceedings of the Workshop on Stylistic Variation, pages 94–104, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Controlling Linguistic Style Aspects in Neural Language Generation (Ficler & Goldberg, Style-Var 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-4912.pdf