An Empirical Study on Multi-Task Learning for Text Style Transfer and Paraphrase Generation
Pawel Bujnowski, Kseniia Ryzhova, Hyungtak Choi, Katarzyna Witkowska, Jaroslaw Piersa, Tymoteusz Krumholc, Katarzyna Beksa
Abstract
The topic of this paper is neural multi-task training for text style transfer. We present an efficient method for neutral-to-style transformation using the transformer framework. We demonstrate how to prepare a robust model utilizing large paraphrases corpora together with a small parallel style transfer corpus. We study how much style transfer data is needed for a model on the example of two transformations: neutral-to-cute on internal corpus and modern-to-antique on publicly available Bible corpora. Additionally, we propose a synthetic measure for the automatic evaluation of style transfer models. We hope our research is a step towards replacing common but limited rule-based style transfer systems by more flexible machine learning models for both public and commercial usage.
BibTeX
@inproceedings{bujnowski-etal-2020-empirical,
title = "An Empirical Study on Multi-Task Learning for Text Style Transfer and Paraphrase Generation",
author = "Bujnowski, Pawel and
Ryzhova, Kseniia and
Choi, Hyungtak and
Witkowska, Katarzyna and
Piersa, Jaroslaw and
Krumholc, Tymoteusz and
Beksa, Katarzyna",
editor = "Clifton, Ann and
Napoles, Courtney",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics: Industry Track",
month = dec,
year = "2020",
address = "Online",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-industry.6/",
doi = "10.18653/v1/2020.coling-industry.6",
pages = "50--63"
}