MelodyYue

bert-for-task

CNN-in-Answer-selection

WikiQA，复现论文《APPLYING DEEP LEARNING TO ANSWER SELECTION: A STUDY AND AN OPEN TASK》

GradNorm

This is a demo implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks.

insuranceQA

A question answering corpus in insurance domain

Multitask-Recommendation-Library

MTReclib provides a PyTorch implementation of multi-task recommendation models and common datasets.

pytorch-grad-norm

Pytorch implementation of the GradNorm. GradNorm addresses the problem of balancing multiple losses for multi-task learning by learning adjustable weight coefficients.

tencent-ml-images

Largest multi-label image database; ResNet-101 model; 80.73% top-1 acc on ImageNet

TensorFlowLaboratory

Research about Tensorflow

word2vector-Chinese-tensorflow

word2vector For Chinese with tensorflow