Related papers: A Probabilistic Formulation of Unsupervised Text S…

We present an unsupervised word segmentation model, in which the learning objective is to maximize the generation probability of a sentence given its all possible segmentation. Such generation probability can be factorized into the…

We introduce a new approach to probabilistic unsupervised learning based on the recognition-parametrised model (RPM): a normalised semi-parametric hypothesis class for joint distributions over observed and latent variables. Under the key…

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…

As the amount of textual data has been rapidly increasing over the past decade, efficient similarity search methods have become a crucial component of large-scale information retrieval systems. A popular strategy is to represent original…

Unsupervised style transfer models are mainly based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to the test cases.…

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…

Unsupervised word translation from non-parallel inter-lingual corpora has attracted much research interest. Very recently, neural network methods trained with adversarial loss functions achieved high accuracy on this task. Despite the…

Publicly available, large pretrained LanguageModels (LMs) generate text with remarkable quality, but only sequentially from left to right. As a result, they are not immediately applicable to generation tasks that break the unidirectional…

This paper proposes an unsupervised method for learning a unified representation that serves both discriminative and generative purposes. While most existing unsupervised learning approaches focus on a representation for only one of these…

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…

We propose a new unsupervised method for lexical substitution using pre-trained language models. Compared to previous approaches that use the generative capability of language models to predict substitutes, our method retrieves substitutes…

Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such…

Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inherently sequential and unidirectional generation. While…

This paper presents a novel unsupervised abstractive summarization method for opinionated texts. While the basic variational autoencoder-based models assume a unimodal Gaussian prior for the latent code of sentences, we alternate it with a…

In this article, we investigate the use of a probabilistic model for unsupervised clustering in text collections. Unsupervised clustering has become a basic module for many intelligent text processing applications, such as information…

Autoregressive models have been widely used in unsupervised text style transfer. Despite their success, these models still suffer from the content preservation problem that they usually ignore part of the source sentence and generate some…

We present a novel generative model that combines state-of-the-art neural text-to-speech (TTS) with semi-supervised probabilistic latent variable models. By providing partial supervision to some of the latent variables, we are able to force…

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…

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;…

Computational stylometry studies writing style through quantitative textual patterns, enabling applications such as authorship attribution, identity linking, and plagiarism detection. Existing supervised and contrastive approaches often…