相关论文: Text Generation with Text-Editing Models

Text-to-image generation models have grown in popularity due to their ability to produce high-quality images from a text prompt. One use for this technology is to enable the creation of more accessible art creation software. In this paper,…

Text-guided diffusion models have shown superior performance in image/video generation and editing. While few explorations have been performed in 3D scenarios. In this paper, we discuss three fundamental and interesting problems on this…

Generating realistic sequences is a central task in many machine learning applications. There has been considerable recent progress on building deep generative models for sequence generation tasks. However, the issue of mode-collapsing…

The advent of large pre-trained language models has made it possible to make high-quality predictions on how to add or change a sentence in a document. However, the high branching factor inherent to text generation impedes the ability of…

Large pre-trained language models are capable of generating varied and fluent texts. Starting from the prompt, these models generate a narrative that can develop unpredictably. The existing methods of controllable text generation, which…

Image generation has recently seen tremendous advances, with diffusion models allowing to synthesize convincing images for a large variety of text prompts. In this article, we propose DiffEdit, a method to take advantage of text-conditioned…

Breakthroughs in text-to-music generation models are transforming the creative landscape, equipping musicians with innovative tools for composition and experimentation like never before. However, controlling the generation process to…

As the world changes, we need to be able to update our models and correct false information without costly retraining. Knowledge-based model editing enables precise modifications to the weights of large language models in order to modify…

Natural language (NL) explanations of model predictions are gaining popularity as a means to understand and verify decisions made by large black-box pre-trained models, for NLP tasks such as Question Answering (QA) and Fact Verification.…

Text-to-image generative models are a new and powerful way to generate visual artwork. However, the open-ended nature of text as interaction is double-edged; while users can input anything and have access to an infinite range of…

Data of sequential nature arise in many application domains in forms of, e.g. textual data, DNA sequences, and software execution traces. Different research disciplines have developed methods to learn sequence models from such datasets: (i)…

Table-to-text generation aims at automatically generating natural text to help people to conveniently obtain the important information in tables. Although neural models for table-to-text have achieved remarkable progress, some problems…

Recent developments in neural networks have led to the advance in data-to-text generation. However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications. In…

Text-to-Image (TTI) generative models have shown great progress in the past few years in terms of their ability to generate complex and high-quality imagery. At the same time, these models have been shown to suffer from harmful biases,…

In Natural Language Processing (NLP), it is important to detect the relationship between two sequences or to generate a sequence of tokens given another observed sequence. We call the type of problems on modelling sequence pairs as sequence…

Generative models have long been the dominant approach for speech recognition. The success of these models however relies on the use of sophisticated recipes and complicated machinery that is not easily accessible to non-practitioners.…

We introduce a neural machine translation model that views the input and output sentences as sequences of characters rather than words. Since word-level information provides a crucial source of bias, our input model composes representations…

Recent advances in large-scale pre-training such as GPT-3 allow seemingly high quality text to be generated from a given prompt. However, such generation systems often suffer from problems of hallucinated facts, and are not inherently…

Programming languages are emerging as a challenging and interesting domain for machine learning. A core task, which has received significant attention in recent years, is building generative models of source code. However, to our knowledge,…

Transformer-based models have made tremendous impacts in natural language generation. However the inference speed is a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process. We develop…