相关论文: Auto-Sizing the Transformer Network: Improving Spe…

Bilingual sequence models improve phrase-based translation and reordering by overcoming phrasal independence assumption and handling long range reordering. However, due to data sparsity, these models often fall back to very small context…

Deep learning models have proven to be exceptionally useful in performing many machine learning tasks. However, for each new dataset, choosing an effective size and structure of the model can be a time-consuming process of trial and error.…

Recent research has shown the existence of significant redundancy in large Transformer models. One can prune the redundant parameters without significantly sacrificing the generalization performance. However, we question whether the…

The Vision Transformer architecture is a deep learning model inspired by the success of the Transformer model in Natural Language Processing. However, the self-attention mechanism, large number of parameters, and the requirement for a…

For almost 70 years, researchers have typically selected the width of neural networks' layers either manually or through automated hyperparameter tuning methods such as grid search and, more recently, neural architecture search. This paper…

It is relatively easy to mine a large parallel corpus for any machine learning task, such as speech-to-text or speech-to-speech translation. Although these mined corpora are large in volume, their quality is questionable. This work shows…

Due to the excessive cost of large-scale language model pre-training, considerable efforts have been made to train BERT progressively -- start from an inferior but low-cost model and gradually grow the model to increase the computational…

To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary…

The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…

Despite their empirical success, neural networks still have difficulty capturing compositional aspects of natural language. This work proposes a simple data augmentation approach to encourage compositional behavior in neural models for…

Machine translation (MT) models used in industries with constantly changing topics, such as translation or news agencies, need to adapt to new data to maintain their performance over time. Our aim is to teach a pre-trained MT model to…

Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of…

The increasing size of language models raises great research interests in parameter-efficient fine-tuning such as LoRA that freezes the pre-trained model, and injects small-scale trainable parameters for multiple downstream tasks (e.g.,…

The machine translation mechanism translates texts automatically between different natural languages, and Neural Machine Translation (NMT) has gained attention for its rational context analysis and fluent translation accuracy. However,…

A challenge in spoken language translation is that plenty of spoken content is long-form, but short units are necessary for obtaining high-quality translations. To address this mismatch, we fine-tune a general-purpose, large language model…

Pruning neural networks has regained interest in recent years as a means to compress state-of-the-art deep neural networks and enable their deployment on resource-constrained devices. In this paper, we propose a robust compressive learning…

During the pre-training step of natural language models, the main objective is to learn a general representation of the pre-training dataset, usually requiring large amounts of textual data to capture the complexity and diversity of natural…

Network pruning reduces the computation costs of an over-parameterized network without performance damage. Prevailing pruning algorithms pre-define the width and depth of the pruned networks, and then transfer parameters from the unpruned…

We present novel techniques to accelerate the convergence of Deep Learning algorithms by conducting low overhead removal of redundant neurons -- apoptosis of neurons -- which do not contribute to model learning, during the training phase…

Modern Convolutional Neural Networks (CNNs) are complex, encompassing millions of parameters. Their deployment exerts computational, storage and energy demands, particularly on embedded platforms. Existing approaches to prune or sparsify…