相关论文: Unsupervised Text Style Transfer with Padded Maske…

Text Style Transfer (TST) is performable through approaches such as latent space disentanglement, cycle-consistency losses, prototype editing etc. The prototype editing approach, which is known to be quite successful in TST, involves two…

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…

Unsupervised Text Style Transfer (UTST) has emerged as a critical task within the domain of Natural Language Processing (NLP), aiming to transfer one stylistic aspect of a sentence into another style without changing its semantics, syntax,…

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 work has shown the importance of adaptation of broad-coverage contextualised embedding models on the domain of the target task of interest. Current self-supervised adaptation methods are simplistic, as the training signal comes from…

We present a general framework for unsupervised text style transfer with deep generative models. The framework models each sentence-label pair in the non-parallel corpus as partially observed from a complete quadruplet which additionally…

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…

Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. In the cross-modal setting, tokens in the sentence are masked at random, and the model predicts the masked tokens given the image and the text. In…

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…

Unsupervised text style transfer task aims to rewrite a text into target style while preserving its main content. Traditional methods rely on the use of a fixed-sized vector to regulate text style, which is difficult to accurately convey…

This paper focuses on the task of sentiment transfer on non-parallel text, which modifies sentiment attributes (e.g., positive or negative) of sentences while preserving their attribute-independent content. Due to the limited capability of…

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence…

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…

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. In this work, we propose a semi-supervised formality…

A variety of contextualised language models have been proposed in the NLP community, which are trained on diverse corpora to produce numerous Neural Language Models (NLMs). However, different NLMs have reported different levels of…

We introduce replacing language model (RLM), a sequence-to-sequence language modeling framework for text style transfer (TST). Our method autoregressively replaces each token of the source sentence with a text span that has a similar…

Self-supervised learning has emerged as a powerful approach for leveraging large-scale unlabeled data to improve model performance in various domains. In this paper, we explore masked self-supervised pre-training for text recognition…

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…

Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem…

Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models. However, we argue that simply applying both techniques can be conflicting and even leads to sub-optimal performance. When allocating…