Papers with attribute transfer

3 papers
Reformulating Unsupervised Style Transfer as Paraphrase Generation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing systems for style transfer warp the input’s meaning through attribute transfer, which changes semantic properties such as sentiment.
Approach: They propose a method for fine-tuning pretrained language models on automatically generated paraphrase data to improve the efficiency of style transfer.
Outcome: The proposed method outperforms state-of-the-art style transfer systems on human and automatic evaluations and proposes fixed variants.
Delete, Retrieve, Generate: a Simple Approach to Sentiment and Style Transfer (N18-1)

Copied to clipboard

Challenge: Previous work using adversarial methods has struggled to produce high-quality outputs.
Approach: They propose a method that transforms a sentence to alter a specific attribute while preserving its attribute-independent content.
Outcome: The proposed method generates grammatical and appropriate responses on 22% more inputs than the best previous system, averaged over three attribute transfer datasets.
IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation (D19-1)

Copied to clipboard

Challenge: Existing approaches to rewrite sentences with certain attributes are difficult and often result in poor content-preservation and ungrammaticality.
Approach: They propose a method that uses a sequence-to-sequence model to learn attribute transfer . existing approaches try to explicitly disentangle content and attribute information .
Outcome: The proposed method outperforms complex state-of-the-art systems by a large margin in sentiment modification and formality transfer tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations