Controllable Text Generation with Focused Variation

Lei Shu, Alexandros Papangelis, Yi-Chia Wang, Gokhan Tur, Hu Xu, Zhaleh Feizollahi, Bing Liu, Piero Molino


Abstract
This work introduces Focused-Variation Network (FVN), a novel model to control language generation. The main problems in previous controlled language generation models range from the difficulty of generating text according to the given attributes, to the lack of diversity of the generated texts. FVN addresses these issues by learning disjoint discrete latent spaces for each attribute inside codebooks, which allows for both controllability and diversity, while at the same time generating fluent text. We evaluate FVN on two text generation datasets with annotated content and style, and show state-of-the-art performance as assessed by automatic and human evaluations.
Anthology ID:
2020.findings-emnlp.339
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3805–3817
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.339
DOI:
10.18653/v1/2020.findings-emnlp.339
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.339.pdf