REVIEW 4 cited by
Multiple-Attribute Text Style Transfer
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The dominant approach to unsupervised "style transfer" in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its "style". In this paper, we show that this condition is not necessary and is not always met in practice, even with domain adversarial training that explicitly aims at learning such disentangled representations. We thus propose a new model that controls several factors of variation in textual data where this condition on disentanglement is replaced with a simpler mechanism based on back-translation. Our method allows control over multiple attributes, like gender, sentiment, product type, etc., and a more fine-grained control on the trade-off between content preservation and change of style with a pooling operator in the latent space. Our experiments demonstrate that the fully entangled model produces better generations, even when tested on new and more challenging benchmarks comprising reviews with multiple sentences and multiple attributes.
Forward citations
Cited by 4 Pith papers
-
Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer
A delete-retrieve-generate style transfer system using BERT attention for deleting style words and a GPT-based transformer for generation outperforms prior systems on five non-parallel style transfer datasets.
-
Unsupervised Text Summarization via Mixed Model Back-Translation
A back-translation loop with three asymmetric initialization models (thresholded word alignment, reweighted bag-of-words denoising autoencoder, and word-presence moment matching) produces state-of-the-art unsupervised...
-
Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites
The authors show that standard text style-transfer metrics are unstable and manipulable, recommend BLEU against human rewrites as an additional benchmark, and report three architectures that improve on that metric.
-
Domain Adaptive Text Style Transfer
Domain-adaptive text style transfer using a shared encoder-decoder with domain vectors and domain-specific style classifiers improves low-resource sentiment and formality rewriting.
Discussion (0). Continue with ORCID to comment.