# Improved Neural Text Attribute Transfer with Non-parallel Data

arXiv: https://arxiv.org/abs/1711.09395 · HTML: https://mlsanity.com/paper/1711.09395/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2017.

## Built on by (most cited first, 2 of 2)

- [Methods for Detoxification of Texts for the Russian Language](https://mlsanity.com/paper/2105.09052/) (2021)
- [Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis](https://mlsanity.com/paper/2203.07090/) (2022)

## Abstract (arXiv)

Text attribute transfer using non-parallel data requires methods that can perform disentanglement of content and linguistic attributes. In this work, we propose multiple improvements over the existing approaches that enable the encoder-decoder framework to cope with the text attribute transfer from non-parallel data. We perform experiments on the sentiment transfer task using two datasets. For both datasets, our proposed method outperforms a strong baseline in two of the three employed evaluation metrics.