Papers with style accuracy

5 papers
Contextual Text Style Transfer (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for text style transfer are limited by the lack of parallel data.
Approach: They propose a task to translate a sentence into a desired style with its surrounding context taken into account.
Outcome: The proposed model outperforms state-of-the-art methods across style accuracy, content preservation and contextual consistency metrics.
Diff4TST: Masked Diffusion Language Model for Text Style Transfer (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for text style transfer rely on task-specific training and expensive training stages.
Approach: They propose a diffusion-based language model that formulates text style transfer as an explicit copy-and-edit process.
Outcome: The proposed model improves style accuracy and controllability while maintaining strong content preservation and fluency.
Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites (D19-1)

Copied to clipboard

Challenge: Currently, standard methods for style transfer have several significant problems.
Approach: They propose to take BLEU between input and human-written reformulations into consideration for benchmarks.
Outcome: The proposed architectures outperform state-of-the-art in style transfer metric on human-written reformulations and take BLEU between input and output into consideration for benchmarks.
T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation (2022.emnlp-main)

Copied to clipboard

Challenge: Unavailability of parallel corpora for training text style transfer models is a challenge but common . a large corpus of parallel data is not available for text style transfers .
Approach: They propose to use AMR as an intermediate style agnostic representation to train TST models.
Outcome: The proposed model outperforms state-of-the-art models in the style agnostic task.
Attractive Storyteller: Stylized Visual Storytelling with Unpaired Text (2023.acl-long)

Copied to clipboard

Challenge: Xu et al., 2015; Guo e t al, 2022a) focus on generating objective and neutral descriptions of image content without considering style characteristics.
Approach: They propose a task of Stylized Visual Storytelling to generate attractive stylized stories for a photo stream.
Outcome: The proposed framework can generate attractive stories with different styles . it surpasses state-of-the-art methods on automatic and human evaluation metrics.

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