Related papers: UniDrop: A Simple yet Effective Technique to Impro…
Deep learning models learn to fit training data while they are highly expected to generalize well to testing data. Most works aim at finding such models by creatively designing architectures and fine-tuning parameters. To adapt to…
Recently, nested dropout was proposed as a method for ordering representation units in autoencoders by their information content, without diminishing reconstruction cost. However, it has only been applied to training fully-connected…
Deep neural networks are learning models with a very high capacity and therefore prone to over-fitting. Many regularization techniques such as Dropout, DropConnect, and weight decay all attempt to solve the problem of over-fitting by…
Transformer models, which leverage architectural improvements like self-attention, perform remarkably well on Natural Language Processing (NLP) tasks. The self-attention mechanism is position agnostic. In order to capture positional…
This paper presents a new version of Dropout called Split Dropout (sDropout) and rotational convolution techniques to improve CNNs' performance on image classification. The widely used standard Dropout has advantage of preventing deep…
Very deep convolutional neural networks offer excellent recognition results, yet their computational expense limits their impact for many real-world applications. We introduce BlockDrop, an approach that learns to dynamically choose which…
This paper presents UniBERT, a compact multilingual language model that uses an innovative training framework that integrates three components: masked language modeling, adversarial training, and knowledge distillation. Pre-trained on a…
Reading comprehension has recently seen rapid progress, with systems matching humans on the most popular datasets for the task. However, a large body of work has highlighted the brittleness of these systems, showing that there is much work…
To enhance the generalization ability of the model and improve the effectiveness of the transformer for named entity recognition tasks, the XLNet-Transformer-R model is proposed in this paper. The XLNet pre-trained model and the Transformer…
Text embeddings, i.e. vector representations of entire texts, play an important role in many NLP applications, such as retrieval-augmented generation, clustering, or visualizing collections of texts for data exploration. Currently,…
Model-based reinforcement learning is a widely accepted solution for solving excessive sample demands. However, the predictions of the dynamics models are often not accurate enough, and the resulting bias may incur catastrophic decisions…
With the growing attention on learning-to-learn new tasks using only a few examples, meta-learning has been widely used in numerous problems such as few-shot classification, reinforcement learning, and domain generalization. However,…
We introduce Data Diversification: a simple but effective strategy to boost neural machine translation (NMT) performance. It diversifies the training data by using the predictions of multiple forward and backward models and then merging…
Dropout is often used in deep neural networks to prevent over-fitting. Conventionally, dropout training invokes \textit{random drop} of nodes from the hidden layers of a Neural Network. It is our hypothesis that a guided selection of nodes…
Transformer architectures dominate modern NLP but often demand heavy computational resources and intricate hyperparameter tuning. To mitigate these challenges, we propose a novel framework, BoostTransformer, that augments transformers with…
Machine Translation models are trained to translate a variety of documents from one language into another. However, models specifically trained for a particular characteristics of the documents tend to perform better. Fine-tuning is a…
Real-world data contains a vast amount of multimodal information, among which vision and language are the two most representative modalities. Moreover, increasingly heavier models, \textit{e}.\textit{g}., Transformers, have attracted the…
Adapter-Tuning (AT) method involves freezing a pre-trained model and introducing trainable adapter modules to acquire downstream knowledge, thereby calibrating the model for better adaptation to downstream tasks. This paper proposes a…
We study Transformers through the perspective of optimal control theory, using tools from continuous-time formulations to derive actionable insights into training and architecture design. This framework improves the performance of existing…
Dropout is typically interpreted as bagging a large number of models sharing parameters. We show that using dropout in a network can also be interpreted as a kind of data augmentation in the input space without domain knowledge. We present…