Text Attribute Transfer
5 papers with code • 0 benchmarks • 0 datasets
The goal of the Text Attribute Transfer task is to change an input text such that the value of a particular linguistic attribute of interest (e.g. language = English, sentiment = Positive) is transferred to a different desired value (e.g. language = French, sentiment = Negative). This task needs approaches that can disentangle the content from other linguistic attributes of the text.
Source: Improved Neural Text Attribute Transfer with Non-parallel Data
Benchmarks
These leaderboards are used to track progress in Text Attribute Transfer
Most implemented papers
Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
lijuncen/Sentiment-and-Style-Transfer
•
•
NAACL 2018
We consider the task of text attribute transfer: transforming a sentence to alter a specific attribute (e. g., sentiment) while preserving its attribute-independent content (e. g., changing "screen is just the right size" to "screen is too small").
IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation
Text attribute transfer aims to automatically rewrite sentences such that they possess certain linguistic attributes, while simultaneously preserving their semantic content.
Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation
nrgeup/controllable-text-attribute-transfer
•
•
NeurIPS 2019
Unsupervised text attribute transfer automatically transforms a text to alter a specific attribute (e. g. sentiment) without using any parallel data, while simultaneously preserving its attribute-independent content.
Deep Learning for Text Style Transfer: A Survey
fuzhenxin/Style-Transfer-in-Text
•
•
CL (ACL) 2022
Text style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness, emotion, humor, and many others.
Rethinking Text Attribute Transfer: A Lexical Analysis
We apply this framework to existing datasets and models and show that: (1) the pivot words are strong features for the classification of sentence attributes; (2) to change the attribute of a sentence, many datasets only requires to change certain pivot words; (3) consequently, many transfer models only perform the lexical-level modification, while leaving higher-level sentence structures unchanged.
