ACL 2021short24 citations

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.

BibTeX
@inproceedings{nangi-etal-2021-counterfactuals,
    title = "Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer",
    author = "Nangi, Sharmila Reddy  and
      Chhaya, Niyati  and
      Khosla, Sopan  and
      Kaushik, Nikhil  and
      Nyati, Harshit",
    editor = "Zong, Chengqing  and
      Xia, Fei  and
      Li, Wenjie  and
      Navigli, Roberto",
    booktitle = "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 = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.acl-short.7/",
    doi = "10.18653/v1/2021.acl-short.7",
    pages = "40--48"
}
Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer · ACL 2021