相关论文: Capturing Style in Author and Document Representat…

Distributed word embeddings have yielded state-of-the-art performance in many NLP tasks, mainly due to their success in capturing useful semantic information. These representations assign only a single vector to each word whereas a large…

Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building…

Artistic style transfer aims to transfer the style of an artwork to a photograph while maintaining its original overall content. Many prior works focus on designing various transfer modules to transfer the style statistics to the content…

Character-based neural models have recently proven very useful for many NLP tasks. However, there is a gap of sophistication between methods for learning representations of sentences and words. While most character models for learning…

Text classification is fundamental in natural language processing (NLP), and Graph Neural Networks (GNN) are recently applied in this task. However, the existing graph-based works can neither capture the contextual word relationships within…

The diversity of painting styles represents a rich visual vocabulary for the construction of an image. The degree to which one may learn and parsimoniously capture this visual vocabulary measures our understanding of the higher level…

Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this…

We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable. Drop-Bottleneck not only enjoys a simple and tractable compression objective but also…

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…

Retrieving relevant documents from a corpus is typically based on the semantic similarity between the document content and query text. The inclusion of structural relationship between documents can benefit the retrieval mechanism by…

Word vector embeddings have been shown to contain and amplify biases in data they are extracted from. Consequently, many techniques have been proposed to identify, mitigate, and attenuate these biases in word representations. In this paper,…

In recent years, the increasing use of Artificial Intelligence based text generation tools has posed new challenges in document provenance, authentication, and authorship detection. However, advancements in stylometry have provided…

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…

Statistical methods have been widely employed in many practical natural language processing applications. More specifically, complex networks concepts and methods from dynamical systems theory have been successfully applied to recognize…

Pretrained language models are long known to be subpar in capturing sentence and document-level semantics. Though heavily investigated, transferring perturbation-based methods from unsupervised visual representation learning to NLP remains…

The advent of instruction-tuned language models that convincingly mimic human writing poses a significant risk of abuse. However, such abuse may be counteracted with the ability to detect whether a piece of text was composed by a language…

Distributed dense word vectors have been shown to be effective at capturing token-level semantic and syntactic regularities in language, while topic models can form interpretable representations over documents. In this work, we describe…

Authors writing documents imprint identifying information within their texts: vocabulary, registry, punctuation, misspellings, or even emoji usage. Previous works use hand-crafted features or classification tasks to train their authorship…

In many natural language processing (NLP) tasks, a document is commonly modeled as a bag of words using the term frequency-inverse document frequency (TF-IDF) vector. One major shortcoming of the frequency-based TF-IDF feature vector is…

In standard methodology for natural language processing, entities in text are typically embedded in dense vector spaces with pre-trained models. The embeddings produced this way are effective when fed into downstream models, but they…