Related papers: Same Author or Just Same Topic? Towards Content-In…

Self-training (ST) and self-supervised learning (SSL) methods have demonstrated strong improvements in automatic speech recognition (ASR). In spite of these advances, to the best of our knowledge, there is no analysis of how the composition…

Visual storytelling aims to generate a narrative paragraph from a sequence of images automatically. Existing approaches construct text description independently for each image and roughly concatenate them as a story, which leads to the…

Retrieving indexed documents, not by their topical content but their writing style opens the door for a number of applications in information retrieval (IR). One application is to retrieve textual content of a certain author X, where the…

Recent work has demonstrated that language models can be trained to identify the author of much shorter literary passages than has been thought feasible for traditional stylometry. We replicate these results for authorship and extend them…

Learning robust representations of authorial style is crucial for authorship attribution and AI-generated text detection. However, existing methods often struggle with content-style entanglement, where models learn spurious correlations…

Supervised training of abstractive language generation models results in learning conditional probabilities over language sequences based on the supervised training signal. When the training signal contains a variety of writing styles, such…

Existing research on Authorship Attribution (AA) focuses on texts for which a lot of data is available (e.g novels), mainly in English. We approach AA via Authorship Verification on short Italian texts in two novel datasets, and analyze the…

Recent advances in large language models have created new opportunities for stylometry, the study of writing styles and authorship. Two challenges, however, remain central: training generative models when no paired data exist, and…

Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in representation…

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…

Writing style is a combination of consistent decisions associated with a specific author at different levels of language production, including lexical, syntactic, and structural. In this paper, we introduce a style-aware neural model to…

From the patter of rain to the crunch of snow, the sounds we hear often convey the visual textures that appear within a scene. In this paper, we present a method for learning visual styles from unlabeled audio-visual data. Our model learns…

Unsupervised pre-training is now the predominant approach for both text and speech understanding. Self-attention models pre-trained on large amounts of unannotated data have been hugely successful when fine-tuned on downstream tasks from a…

For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker…

When the visual style of text is considered, a wide variety can be observed in font, color, and size. However, when a word is read, its meaning is independent of the style in which it has been written or rendered. In this paper, we…

Text Style Transfer (TST) is a pivotal task in natural language generation to manipulate text style attributes while preserving style-independent content. The attributes targeted in TST can vary widely, including politeness, authorship,…

We present streaming self-training (SST) that aims to democratize the process of learning visual recognition models such that a non-expert user can define a new task depending on their needs via a few labeled examples and minimal domain…

Despite the impressive advancements achieved through vision-and-language pretraining, it remains unclear whether this joint learning paradigm can help understand each individual modality. In this work, we conduct a comparative analysis of…

Forensic scientists often need to identify an unknown speaker or writer in cases such as ransom calls, covert recordings, alleged suicide notes, or anonymous online communications, among many others. Speaker recognition in the speech domain…

Style transfer is an important problem in natural language processing (NLP). However, the progress in language style transfer is lagged behind other domains, such as computer vision, mainly because of the lack of parallel data and principle…