Search Results for author:
Found 10 papers, 3 papers with code
Learning Bias-reduced Word Embeddings Using Dictionary Definitions
Pre-trained word embeddings, such as GloVe, have shown undesirable gender, racial, and religious biases.
Nichelle and Nancy: The Influence of Demographic Attributes and Tokenization Length on First Name Biases
We find that demographic attributes of a name (race, ethnicity, and gender) and name tokenization length are both factors that systematically affect the behavior of social commonsense reasoning models.
SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models
A common limitation of diagnostic tests for detecting social biases in NLP models is that they may only detect stereotypic associations that are pre-specified by the designer of the test.
Investigating Information Inconsistency in Multilingual Open-Domain Question Answering
Retrieval based open-domain QA systems use retrieved documents and answer-span selection over retrieved documents to find best-answer candidates.
Exploring the Common Principal Subspace of Deep Features in Neural Networks
Specifically, we design a new metric $\mathcal{P}$-vector to represent the principal subspace of deep features learned in a DNN, and propose to measure angles between the principal subspaces using $\mathcal{P}$-vectors.
Can We Use Gradient Norm as a Measure of Generalization Error for Model Selection in Practice?
The recent theoretical investigation (Li et al., 2020) on the upper bound of generalization error of deep neural networks (DNNs) demonstrates the potential of using the gradient norm as a measure that complements validation accuracy for model selection in practice.
Empirical Studies on the Convergence of Feature Spaces in Deep Learning
While deep learning is effective to learn features/representations from data, the distributions of samples in feature spaces learned by various architectures for different training tasks (e. g., latent layers of AEs and feature vectors in CNN classifiers) have not been well-studied or compared.
XMixup: Efficient Transfer Learning with Auxiliary Samples by Cross-domain Mixup
While the existing multitask learning algorithms need to run backpropagation over both the source and target datasets and usually consume a higher gradient complexity, XMixup transfers the knowledge from source to target tasks more efficiently: for every class of the target task, XMixup selects the auxiliary samples from the source dataset and augments training samples via the simple mixup strategy.
RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr
RIFLE brings meaningful updates to the weights of deep CNN layers and improves low-level feature learning, while the effects of randomization can be easily converged throughout the overall learning procedure.
COLAM: Co-Learning of Deep Neural Networks and Soft Labels via Alternating Minimization
Softening labels of training datasets with respect to data representations has been frequently used to improve the training of deep neural networks (DNNs).
