Related papers: Residual Energy-Based Models for Text

We present a comparison of word-based and character-based sequence-to-sequence models for data-to-text natural language generation, which generate natural language descriptions for structured inputs. On the datasets of two recent generation…

Text-to-audio models have recently emerged as a powerful technology for generating sound from textual descriptions. However, their high computational demands raise concerns about energy consumption and environmental impact. In this paper,…

Modeling long-term dependencies for audio signals is a particularly challenging problem, as even small-time scales yield on the order of a hundred thousand samples. With the recent advent of Transformers, neural architectures became good at…

When parsing unrestricted language, wide-covering grammars often undergenerate. Undergeneration can be tackled either by sentence correction, or by grammar correction. This thesis concentrates upon automatic grammar correction (or machine…

We propose a generic and interpretable learning framework for building robust text classification model that achieves accuracy comparable to full models under test-time budget constraints. Our approach learns a selector to identify words…

The impressive capacity shown by recent text-to-image diffusion models to generate high-quality pictures from textual input prompts has leveraged the debate about the very definition of art. Nonetheless, these models have been trained using…

Deep generative models produce data according to a learned representation, e.g. diffusion models, through a process of approximation computing possible samples. Approximation can be understood as reconstruction and the large datasets used…

One of the latest applications of Artificial Intelligence (AI) is to generate images from natural language descriptions. These generators are now becoming available and achieve impressive results that have been used for example in the front…

We propose a novel approach for using unsupervised boosting to create an ensemble of generative models, where models are trained in sequence to correct earlier mistakes. Our meta-algorithmic framework can leverage any existing base learner…

Exposure bias has been regarded as a central problem for auto-regressive language models (LM). It claims that teacher forcing would cause the test-time generation to be incrementally distorted due to the training-generation discrepancy.…

Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving attributes like speaker and emotion, serving as foundation models for spoken dialogue. In prior…

We improve the informativeness of models for conditional text generation using techniques from computational pragmatics. These techniques formulate language production as a game between speakers and listeners, in which a speaker should…

The ability of large language models to generate complex texts allows them to be widely integrated into many aspects of life, and their output can quickly fill all network resources. As the impact of LLMs grows, it becomes increasingly…

Text generative models (TGMs) excel in producing text that matches the style of human language reasonably well. Such TGMs can be misused by adversaries, e.g., by automatically generating fake news and fake product reviews that can look…

Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders, also trained on raw text, but with the…

Controlled text generation allows for enforcing user-defined constraints on large language model outputs, an increasingly important field as LLMs become more prevalent in everyday life. One common approach uses energy-based decoding, which…

Recent work has explored integrating autoregressive language models with energy-based models (EBMs) to enhance text generation capabilities. However, learning effective EBMs for text is challenged by the discrete nature of language. This…

A generative recurrent neural network is quickly trained in an unsupervised manner to model popular reinforcement learning environments through compressed spatio-temporal representations. The world model's extracted features are fed into…

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…

Neural text generation models are often autoregressive language models or seq2seq models. These models generate text by sampling words sequentially, with each word conditioned on the previous word, and are state-of-the-art for several…