Related papers: Unsupervised Text Style Transfer with Deep Generat…

We present a deep generative model for unsupervised text style transfer that unifies previously proposed non-generative techniques. Our probabilistic approach models non-parallel data from two domains as a partially observed parallel…

Unsupervised text style transfer aims at training a generative model that can alter the style of the input sentence while preserving its content without using any parallel data. In this paper, we employ powerful pre-trained large language…

Automatic transfer of text between domains has become popular in recent times. One of its aims is to preserve the semantic content of text being translated from source to target domain. However, it does not explicitly maintain other…

Text style transfer task requires the model to transfer a sentence of one style to another style while retaining its original content meaning, which is a challenging problem that has long suffered from the shortage of parallel data. In this…

Unsupervised text style transfer aims to transfer the underlying style of text but keep its main content unchanged without parallel data. Most existing methods typically follow two steps: first separating the content from the original…

Text-style transfer aims to convert text given in one domain into another by paraphrasing the sentence or substituting the keywords without altering the content. By necessity, state-of-the-art methods have evolved to accommodate nonparallel…

Text style transfer aims to alter the style of a sentence while preserving its content. Due to the lack of parallel corpora, most recent work focuses on unsupervised methods and often uses cycle construction to train models. Since cycle…

Language style transferring rephrases text with specific stylistic attributes while preserving the original attribute-independent content. One main challenge in learning a style transfer system is a lack of parallel data where the source…

Text style transfer is an important task in controllable language generation. Supervised approaches have pushed performance improvement on style-oriented rewriting such as formality conversion. However, challenges remain due to the scarcity…

We propose Masker, an unsupervised text-editing method for style transfer. To tackle cases when no parallel source-target pairs are available, we train masked language models (MLMs) for both the source and the target domain. Then we find…

Binary classifiers are often employed as discriminators in GAN-based unsupervised style transfer systems to ensure that transferred sentences are similar to sentences in the target domain. One difficulty with this approach is that the error…

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…

Text style transfer is a challenging text generation problem, which aims at altering the style of a given sentence to a target one while keeping its content unchanged. Since there is a natural scarcity of parallel datasets, recent works…

Unsupervised text attribute transfer automatically transforms a text to alter a specific attribute (e.g. sentiment) without using any parallel data, while simultaneously preserving its attribute-independent content. The dominant approaches…

Sentence embeddings are an important component of many natural language processing (NLP) systems. Like word embeddings, sentence embeddings are typically learned on large text corpora and then transferred to various downstream tasks, such…

The performance of existing text style transfer models is severely limited by the non-parallel datasets on which the models are trained. In non-parallel datasets, no direct mapping exists between sentences of the source and target style;…

Recent advancements in language representation learning primarily emphasize language modeling for deriving meaningful representations, often neglecting style-specific considerations. This study addresses this gap by creating generic,…

Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals. Despite the use of large-scale unlabeled data, the performance of unsupervised methods typically lags far behind that of…

We introduce a language generative model framework for generating a styled paragraph based on a context sentence and a style reference example. The framework consists of a style encoder and a texts decoder. The style encoder extracts a…

This work presents methods for learning cross-lingual sentence representations using paired or unpaired bilingual texts. We hypothesize that the cross-lingual alignment strategy is transferable, and therefore a model trained to align only…