SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.00449 · ACL · 2021

Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalization

Nevin Zhang, Dongkyu Lee, Zhiliang Tian, Lanqing Xue

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Text style transfer aims to alter the style (e.g., sentiment) of a sentence while preserving its content. A common approach is to map a given sentence to content representation that is free of style, and the content representation is fed to a decoder with a target style. Previous methods in filtering style completely remove tokens with style at the token level, which incurs the loss of content information. In this paper, we propose to enhance content preservation by implicitly removing the style information of each token with reverse attention, and thereby retain the content. Furthermore, we fuse content information when building the target style representation, making it dynamic with respect to the content. Our method creates not only styleindependent content representation, but also content-dependent style representation in transferring style. Empirical results show that our method outperforms the state-of-the-art baselines by a large margin in terms of content preservation. In addition, it is also competitive in terms of style transfer accuracy and fluency.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2108.00449")
get_code_for_paper("2108.00449")
have("2108.00449")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2108.00449.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2108.00449.svg)](https://syntology.ai/paper/2108.00449)

Connect an agent — have() is free.