Search Results for author:
Found 11 papers, 2 papers with code
Improving Bias Mitigation through Bias Experts in Natural Language Understanding
To mitigate the detrimental effect of the bias on the networks, previous works have proposed debiasing methods that down-weight the biased examples identified by an auxiliary model, which is trained with explicit bias labels.
Learning From Drift: Federated Learning on Non-IID Data via Drift Regularization
In this work, we carefully analyze the existing methods in heterogeneous environments.
Dynamic Structure Pruning for Compressing CNNs
In this work, we introduce a novel structure pruning method, termed as dynamic structure pruning, to identify optimal pruning granularities for intra-channel pruning.
Phase-shifted Adversarial Training
Comprehensive results show that PhaseAT significantly improves the convergence for high-frequency information.
In Defense of Core-set: A Density-aware Core-set Selection for Active Learning
The strategy is to estimate the density of the unlabeled samples and select diverse samples mainly from sparse regions.
Context-based Virtual Adversarial Training for Text Classification with Noisy Labels
In this paper, we propose context-based virtual adversarial training (ConVAT) to prevent a text classifier from overfitting to noisy labels.
An Interpretable Framework for Drug-Target Interaction with Gated Cross Attention
In silico prediction of drug-target interactions (DTI) is significant for drug discovery because it can largely reduce timelines and costs in the drug development process.
Multi-pretraining for Large-scale Text Classification
In addition, we propose a weakly supervised pretraining, where labels for text classification are obtained automatically from an existing approach.
Adaptive Compression of Word Embeddings
However, unlike prior works that assign the same length of codes to all words, we adaptively assign different lengths of codes to each word by learning downstream tasks.
Representation Learning for Unseen Words by Bridging Subwords to Semantic Networks
In the first stage, we learn subword embeddings from the pre-trained word embeddings by using an additive composition function of subwords.
Learning to Generate Word Representations using Subword Information
Unlike previous models that learn word representations from a large corpus, we take a set of pre-trained word embeddings and generalize it to word entries, including OOV words.
