相关论文: Charformer: Fast Character Transformers via Gradie…

Transformer-based architectures have become the de-facto standard models for a wide range of Natural Language Processing tasks. However, their memory footprint and high latency are prohibitive for efficient deployment and inference on…

The Transformer model is widely used in natural language processing for sentence representation. However, the previous Transformer-based models focus on function words that have limited meaning in most cases and could merely extract…

Due to the sparsity of features, noise has proven to be a great inhibitor in the classification of handwritten characters. To combat this, most techniques perform denoising of the data before classification. In this paper, we consolidate…

Recently, significant advancements have been made in diffusion-based visual text generation models. Although the effectiveness of these methods in visual text rendering is rapidly improving, they still encounter challenges such as…

Short text classification is a crucial and challenging aspect of Natural Language Processing. For this reason, there are numerous highly specialized short text classifiers. However, in recent short text research, State of the Art (SOTA)…

Discovering new materials better suited to specific purposes is an important issue in improving the quality of human life. Here, a neural network that creates molecules that meet some desired conditions based on a deep understanding of…

We investigate the potential of stochastic neural networks for learning effective waveform-based acoustic models. The waveform-based setting, inherent to fully end-to-end speech recognition systems, is motivated by several comparative…

Transformers are responsible for the vast majority of recent advances in natural language processing. The majority of practical natural language processing applications of these models are typically enabled through transfer learning. This…

Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…

Transformers have emerged as the underpinning architecture for Large Language Models (LLMs). In generative language models, the inference process involves two primary phases: prompt processing and token generation. Token generation, which…

Recently, end-to-end sequence-to-sequence models for speech recognition have gained significant interest in the research community. While previous architecture choices revolve around time-delay neural networks (TDNN) and long short-term…

We show that standard Transformers without graph-specific modifications can lead to promising results in graph learning both in theory and practice. Given a graph, we simply treat all nodes and edges as independent tokens, augment them with…

Language models (LM) have grown with non-stop in the last decade, from sequence-to-sequence architectures to the state-of-the-art and utter attention-based Transformers. In this work, we demonstrate how the inclusion of deep generative…

We propose a finite-state transducer (FST) representation for the models used to decode keyboard inputs on mobile devices. Drawing from learnings from the field of speech recognition, we describe a decoding framework that can satisfy the…

Character-based translation has several appealing advantages, but its performance is in general worse than a carefully tuned BPE baseline. In this paper we study the impact of character-based input and output with the Transformer…

Research at the intersection of personality psychology, computer science, and linguistics has recently focused increasingly on modeling and predicting personality from language use. We report two major improvements in predicting personality…

Degraded images commonly exist in the general sources of character images, leading to unsatisfactory character recognition results. Existing methods have dedicated efforts to restoring degraded character images. However, the denoising…

End-to-end text spotting is a vital computer vision task that aims to integrate scene text detection and recognition into a unified framework. Typical methods heavily rely on Region-of-Interest (RoI) operations to extract local features and…

Many large language model applications require conditioning on long contexts. Transformers typically support this by storing a large per-layer KV-cache of past activations, which incurs substantial memory overhead. A desirable alternative…

While the Transformer architecture has achieved remarkable success across various domains, a thorough theoretical foundation explaining its optimization dynamics is yet to be fully developed. In this study, we aim to bridge this…