Multi-Style Transfer with Discriminative Feedback on Disjoint Corpus

Navita Goyal, Balaji Vasan Srinivasan, Anandhavelu N, Abhilasha Sancheti


Abstract
Style transfer has been widely explored in natural language generation with non-parallel corpus by directly or indirectly extracting a notion of style from source and target domain corpus. A common shortcoming of existing approaches is the prerequisite of joint annotations across all the stylistic dimensions under consideration. Availability of such dataset across a combination of styles limits the extension of these setups to multiple style dimensions. While cascading single-dimensional models across multiple styles is a possibility, it suffers from content loss, especially when the style dimensions are not completely independent of each other. In our work, we relax this requirement of jointly annotated data across multiple styles by using independently acquired data across different style dimensions without any additional annotations. We initialize an encoder-decoder setup with transformer-based language model pre-trained on a generic corpus and enhance its re-writing capability to multiple target style dimensions by employing multiple style-aware language models as discriminators. Through quantitative and qualitative evaluation, we show the ability of our model to control styles across multiple style dimensions while preserving content of the input text. We compare it against baselines involving cascaded state-of-the-art uni-dimensional style transfer models.
Anthology ID:
2021.naacl-main.275
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3500–3510
Language:
URL:
https://aclanthology.org/2021.naacl-main.275
DOI:
10.18653/v1/2021.naacl-main.275
Bibkey:
Cite (ACL):
Navita Goyal, Balaji Vasan Srinivasan, Anandhavelu N, and Abhilasha Sancheti. 2021. Multi-Style Transfer with Discriminative Feedback on Disjoint Corpus. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3500–3510, Online. Association for Computational Linguistics.
Cite (Informal):
Multi-Style Transfer with Discriminative Feedback on Disjoint Corpus (Goyal et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.275.pdf
Video:
 https://aclanthology.org/2021.naacl-main.275.mp4
Data
GYAFC