Related papers: General Framework for Reversible Data Hiding in Te…

Generating textual descriptions for images has been an attractive problem for the computer vision and natural language processing researchers in recent years. Dozens of models based on deep learning have been proposed to solve this problem.…

Deep learning methods have recently achieved great empirical success on machine translation, dialogue response generation, summarization, and other text generation tasks. At a high level, the technique has been to train end-to-end neural…

Sentence embeddings can be decoded to give approximations of the original texts used to create them. We explore this effect in the context of text simplification, demonstrating that reconstructed text embeddings preserve complexity levels.…

Learning disentangled representations of natural language is essential for many NLP tasks, e.g., conditional text generation, style transfer, personalized dialogue systems, etc. Similar problems have been studied extensively for other forms…

Word embeddings have been shown adept at capturing the semantic and syntactic regularities of the natural language text, as a result of which these representations have found their utility in a wide variety of downstream content analysis…

Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can simply project tokens in a continuous space of embeddings, as…

We propose a new word embedding model, called SPhrase, that incorporates supervised phrase information. Our method modifies traditional word embeddings by ensuring that all target words in a phrase have exactly the same context. We…

The current approach of information hiding based on deep learning model can not directly use the original data as carriers, which means the approach can not make use of the existing data in big data to hiding information. We proposed a…

Large language models are shown to memorize privacy information such as social security numbers in training data. Given the sheer scale of the training corpus, it is challenging to screen and filter these privacy data, either manually or…

We show state-of-the-art word representation learning methods maximize an objective function that is a lower bound on the mutual information between different parts of a word sequence (i.e., a sentence). Our formulation provides an…

In this paper, we propose a reversible data hiding method in the spatial domain for compressed grayscale images. The proposed method embeds secret bits into a compressed thumbnail of the original image by using a novel interpolation method…

Word embeddings trained on large corpora have shown to encode high levels of unfair discriminatory gender, racial, religious and ethnic biases. In contrast, human-written dictionaries describe the meanings of words in a concise, objective…

Federated learning allows distributed users to collaboratively train a model while keeping each user's data private. Recently, a growing body of work has demonstrated that an eavesdropping attacker can effectively recover image data from…

In recent years, reversible data hiding (RDH), a new research hotspot in the field of information security, has been paid more and more attention by researchers. Most of the existing RDH schemes do not fully take it into account that…

Humans are accustomed to reading and writing in a forward manner, and this natural bias extends to text understanding in auto-regressive large language models (LLMs). This paper investigates whether LLMs, like humans, struggle with reverse…

Most existing image restoration methods use neural networks to learn strong image-level priors from huge data to estimate the lost information. However, these works still struggle in cases when images have severe information deficits.…

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…

Recent research has shown that word embedding spaces learned from text corpora of different languages can be aligned without any parallel data supervision. Inspired by the success in unsupervised cross-lingual word embeddings, in this paper…

This work addresses the challenge of capturing the complexities of legal knowledge by proposing a multi-layered embedding-based retrieval method for legal and legislative texts. Creating embeddings not only for individual articles but also…

The lack of data democratization and information leakage from trained models hinder the development and acceptance of robust deep learning-based healthcare solutions. This paper argues that irreversible data encoding can provide an…