Search Results for author:
Found 10 papers, 6 papers with code
Early Stopping Based on Unlabeled Samples in Text Classification
The proposed method is advantageous because it does not require a separate validation set and provides a better stopping point by using a large unlabeled set.
Domain Knowledge Transferring for Pre-trained Language Model via Calibrated Activation Boundary Distillation
In this study, we propose a domain knowledge transferring (DoKTra) framework for PLMs without additional in-domain pretraining.
Deep Metric Loss for Multimodal Learning
Multimodal learning often outperforms its unimodal counterparts by exploiting unimodal contributions and cross-modal interactions.
PINNet: a deep neural network with pathway prior knowledge for Alzheimer's disease
PINNet is a deep neural network (DNN) model with pathway prior knowledge from either the Gene Ontology or Kyoto Encyclopedia of Genes and Genomes databases.
SDGCCA: Supervised Deep Generalized Canonical Correlation Analysis for Multi-omics Integration
We propose a novel method of multi-omics integration called supervised deep generalized canonical correlation analysis (SDGCCA) for modeling correlation structures between nonlinear multi-omics manifolds, aiming for improving classification of phenotypes and revealing biomarkers related to phenotypes.
A molecular generative model with genetic algorithm and tree search for cancer samples
FasterGTS is constructed with a genetic algorithm and a Monte Carlo tree search with three deep neural networks: supervised learning, self-trained, and value networks, and it generates anticancer molecules based on the genetic profiles of a cancer sample.
Exploiting all samples in low-resource sentence classification: early stopping and initialization parameters
Finally, the proposed learning strategy is to train all samples with the good initialization parameters and stop the model with the early stopping techniques.
Extracting Chemical-Protein Interactions via Calibrated Deep Neural Network and Self-training
To estimate the data uncertainty and improve the reliability, "calibration" techniques have been applied to deep learning models.
DMCB at SemEval-2018 Task 1: Transfer Learning of Sentiment Classification Using Group LSTM for Emotion Intensity prediction
This paper describes a system attended in the SemEval-2018 Task 1 {``}Affect in tweets{''} that predicts emotional intensities.
GIST at SemEval-2018 Task 12: A network transferring inference knowledge to Argument Reasoning Comprehension task
A key idea for our system is full use of transfer learning from the Natural Language Inference (NLI) task to this task.
