Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer

Abstract

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"). Our training data includes only sentences labeled with their attribute (e.g., positive or negative), but not pairs of sentences that differ only in their attributes, so we must learn to disentangle attributes from attribute-independent content in an unsupervised way. Previous work using adversarial methods has struggled to produce high-quality outputs. In this paper, we propose simpler methods motivated by the observation that text attributes are often marked by distinctive phrases (e.g., "too small"). Our strongest method extracts content words by deleting phrases associated with the sentence's original attribute value, retrieves new phrases associated with the target attribute, and uses a neural model to fluently combine these into a final output. On human evaluation, our best method generates grammatical and appropriate responses on 22% more inputs than the best previous system, averaged over three attribute transfer datasets: altering sentiment of reviews on Yelp, altering sentiment of reviews on Amazon, and altering image captions to be more romantic or humorous.

NAACL 2018

References in corpus (6)

• ADADELTA: An Adaptive Learning Rate Method
• Improved Techniques for Training GANs
• Unsupervised Machine Translation Using Monolingual Corpora Only
• Toward Controlled Generation of Text
• Unsupervised Neural Machine Translation
• Improved Neural Text Attribute Transfer with Non-parallel Data

Cited by in corpus (11)

• Multiple-Attribute Text Style Transfer
• Unsupervised Text Style Transfer using Language Models as Discriminators
• CoCon: A Self-Supervised Approach for Controlled Text Generation
• Language Style Transfer from Sentences with Arbitrary Unknown Styles
• Data-to-Text Generation with Style Imitation
• Improving Robustness and Generality of NLP Models Using Disentangled Representations
• Generating similes effortlessly like a Pro: A Style Transfer Approach for Simile Generation
• ST${}^2$: Small-data Text Style Transfer via Multi-task Meta-Learning
• Paraphrase Generation as Unsupervised Machine Translation
• Multi-Pair Text Style Transfer on Unbalanced Data
• An Empirical Study of Extrapolation in Text Generation with Scalar Control