Controlled Text Generation with Adversarial Learning

Federico Betti, Giorgia Ramponi, Massimo Piccardi


Abstract
In recent years, generative adversarial networks (GANs) have started to attain promising results also in natural language generation. However, the existing models have paid limited attention to the semantic coherence of the generated sentences. For this reason, in this paper we propose a novel network – the Controlled TExt generation Relational Memory GAN (CTERM-GAN) – that uses an external input to influence the coherence of sentence generation. The network is composed of three main components: a generator based on a Relational Memory conditioned on the external input; a syntactic discriminator which learns to discriminate between real and generated sentences; and a semantic discriminator which assesses the coherence with the external conditioning. Our experiments on six probing datasets have showed that the model has been able to achieve interesting results, retaining or improving the syntactic quality of the generated sentences while significantly improving their semantic coherence with the given input.
Anthology ID:
2020.inlg-1.5
Volume:
Proceedings of the 13th International Conference on Natural Language Generation
Month:
December
Year:
2020
Address:
Dublin, Ireland
Editors:
Brian Davis, Yvette Graham, John Kelleher, Yaji Sripada
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
29–34
Language:
URL:
https://aclanthology.org/2020.inlg-1.5
DOI:
10.18653/v1/2020.inlg-1.5
Bibkey:
Cite (ACL):
Federico Betti, Giorgia Ramponi, and Massimo Piccardi. 2020. Controlled Text Generation with Adversarial Learning. In Proceedings of the 13th International Conference on Natural Language Generation, pages 29–34, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Controlled Text Generation with Adversarial Learning (Betti et al., INLG 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2020.inlg-1.5.pdf
Supplementary attachment:
 2020.inlg-1.5.Supplementary_Attachment.pdf