Related papers: The Cursive Transformer
While there have been several contributions exploring state of the art techniques for text normalization, the problem of inverse text normalization (ITN) remains relatively unexplored. The best known approaches leverage finite state…
Transformer-based models have achieved remarkable results in low-level vision tasks including image super-resolution (SR). However, early Transformer-based approaches that rely on self-attention within non-overlapping windows encounter…
Transformers are the backbone of powerful foundation models for many Vision and Natural Language Processing tasks. But their compute and memory/storage footprint is large, and so, serving such models is expensive often requiring high-end…
In this paper, we propose a diffusion probabilistic model for handwriting generation. Diffusion models are a class of generative models where samples start from Gaussian noise and are gradually denoised to produce output. Our method of…
Large-scale pre-trained language models, such as BERT and GPT-2, have achieved excellent performance in language representation learning and free-form text generation. However, these models cannot be directly employed to generate text under…
Transformer models are not only successful in natural language processing (NLP) but also demonstrate high potential in computer vision (CV). Despite great advance, most of works only focus on improvement of architectures but pay little…
This paper presents an simple yet sophisticated approach to the challenge by Sproat and Jaitly (2016)- given a large corpus of written text aligned to its normalized spoken form, train an RNN to learn the correct normalization function.…
Ideally, 360{\deg} imagery could inherit the deep convolutional neural networks (CNNs) already trained with great success on perspective projection images. However, existing methods to transfer CNNs from perspective to spherical images…
Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. At the core of the Transformer is the…
In this paper, we address a challenging task, synchronous motion captioning, that aim to generate a language description synchronized with human motion sequences. This task pertains to numerous applications, such as aligned sign language…
In traditional conversational intelligence from speech, a cascaded pipeline is used, involving tasks such as voice activity detection, diarization, transcription, and subsequent processing with different NLP models for tasks like semantic…
Unsupervised image retrieval aims to learn the important visual characteristics without any given level to retrieve the similar images for a given query image. The Convolutional Neural Network (CNN)-based approaches have been extensively…
We report on novel investigations into training models that make sentences concise. We define the task and show that it is different from related tasks such as summarization and simplification. For evaluation, we release two test sets,…
Pre-trained Transformer models like T5 and BART have advanced the state of the art on a wide range of text generation tasks. Compressing these models into smaller ones has become critically important for practical use. Common neural network…
This paper shows how Long Short-term Memory recurrent neural networks can be used to generate complex sequences with long-range structure, simply by predicting one data point at a time. The approach is demonstrated for text (where the data…
Can pre-trained BERT for one language and GPT for another be glued together to translate texts? Self-supervised training using only monolingual data has led to the success of pre-trained (masked) language models in many NLP tasks. However,…
We consider compressive sensing as a source coding method for signal transmission. We concatenate a convolutional coding system with 1-bit compressive sensing to obtain a serial concatenated system model for sparse signal transmission over…
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has…
Transformers have achieved great success across a wide range of applications, yet the theoretical foundations underlying their success remain largely unexplored. To demystify the strong capacities of transformers applied to versatile…
State-of-the-art language models are autoregressive and operate on subword units known as tokens. Specifically, one must encode the conditioning string into a list of tokens before passing to the language models for next-token prediction.…