Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer

Sharmila Reddy Nangi, Niyati Chhaya, Sopan Khosla, Nikhil Kaushik, Harshit Nyati


Abstract
Disentanglement of latent representations into content and style spaces has been a commonly employed method for unsupervised text style transfer. These techniques aim to learn the disentangled representations and tweak them to modify the style of a sentence. In this paper, we propose a counterfactual-based method to modify the latent representation, by posing a ‘what-if’ scenario. This simple and disciplined approach also enables a fine-grained control on the transfer strength. We conduct experiments with the proposed methodology on multiple attribute transfer tasks like Sentiment, Formality and Excitement to support our hypothesis.
Anthology ID:
2021.acl-short.7
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
40–48
Language:
URL:
https://aclanthology.org/2021.acl-short.7
DOI:
10.18653/v1/2021.acl-short.7
Bibkey:
Cite (ACL):
Sharmila Reddy Nangi, Niyati Chhaya, Sopan Khosla, Nikhil Kaushik, and Harshit Nyati. 2021. Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 40–48, Online. Association for Computational Linguistics.
Cite (Informal):
Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer (Nangi et al., ACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.7.pdf
Data
GYAFC