Formality Style Transfer

8 papers with code • 1 benchmarks • 1 datasets

Formality Style Transfer

Datasets


Most implemented papers

Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfer

fuzhenxin/Style-Transfer-in-Text EMNLP 2021

While the field of style transfer (ST) has been growing rapidly, it has been hampered by a lack of standardized practices for automatic evaluation.

Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer

raosudha89/GYAFC-corpus NAACL 2018

Style transfer is the task of automatically transforming a piece of text in one particular style into another.

Parallel Data Augmentation for Formality Style Transfer

lancopku/Augmented_Data_for_FST ACL 2020

The main barrier to progress in the task of Formality Style Transfer is the inadequacy of training data.

Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximization

GT-SALT/FormalityStyleTransfer Findings of the Association for Computational Linguistics 2020

Formality style transfer is the task of converting informal sentences to grammatically-correct formal sentences, which can be used to improve performance of many downstream NLP tasks.

Formality Style Transfer with Shared Latent Space

jimth001/formality_style_transfer_with_shared_latent_space COLING 2020

Conventional approaches for formality style transfer borrow models from neural machine translation, which typically requires massive parallel data for training.

XFORMAL: A Benchmark for Multilingual Formality Style Transfer

Elbria/xformal-FoST 8 Apr 2021

We take the first step towards multilingual style transfer by creating and releasing XFORMAL, a benchmark of multiple formal reformulations of informal text in Brazilian Portuguese, French, and Italian.

Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer

laihuiyuan/Pre-trained-formality-transfer ACL 2021

Scarcity of parallel data causes formality style transfer models to have scarce success in preserving content.

Semi-Supervised Formality Style Transfer with Consistency Training

aolius/semi-fst ACL 2022

In this work, we propose a simple yet effective semi-supervised framework to better utilize source-side unlabeled sentences based on consistency training.