Pith. sign in

REVIEW 4 cited by

Reformulating Unsupervised Style Transfer as Paraphrase Generation

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

arxiv 2010.05700 v1 pith:T46GXTRN submitted 2020-10-12 cs.CL

classification cs.CL
keywords styletransferparaphrasesystemsautomaticexistinggenerationunsupervised
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Modern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfer systems should be paraphrases of their inputs. However, many existing systems purportedly designed for style transfer inherently warp the input's meaning through attribute transfer, which changes semantic properties such as sentiment. In this paper, we reformulate unsupervised style transfer as a paraphrase generation problem, and present a simple methodology based on fine-tuning pretrained language models on automatically generated paraphrase data. Despite its simplicity, our method significantly outperforms state-of-the-art style transfer systems on both human and automatic evaluations. We also survey 23 style transfer papers and discover that existing automatic metrics can be easily gamed and propose fixed variants. Finally, we pivot to a more real-world style transfer setting by collecting a large dataset of 15M sentences in 11 diverse styles, which we use for an in-depth analysis of our system.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Attacks on Machine-Text Detectors Retain Stylistic Fingerprints

    cs.CL 2025-05 conditional novelty 7.0 of 10

    A style-aware paraphrasing attack evades all nine tested AI-text detectors at the single-document level, but multi-document analysis makes the attack detectable again.

  2. Performance Analysis and Optimization for Laser-Phase-Noise based Quantum Random Number Generation

    quant-ph 2026-04 unverdicted novelty 6.0 of 10

    A validated physical model predicts power spectrum and raw-data distributions for laser-phase-noise QRNGs, enabling quantitative rate optimization and proactive photonic-integrated design.

  3. Steering Large Language Models with Register Analysis for Arbitrary Style Transfer

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Register-guided prompting improves meaning preservation in example-based arbitrary style transfer with similar-to-better style strength than prior strategies.

  4. aiXamine: Simplified LLM Safety and Security

    cs.CR 2025-04 conditional novelty 5.0 of 10

    The paper presents aiXamine, a black-box LLM safety and security evaluation platform that aggregates 40+ existing benchmarks into 8 services, and reports a leaderboard of 16 models showing specific vulnerabilities in ...

Pith tools