资源分类
》 资源 》算法》QANet-for-SQuAD-2.0

QANet-for-SQuAD-2.0

2020-02-20 | |  32 |   0 |   0

QANet for SQuAD 2.0

Introduction

Implementation of QANet for SQuAD 2.0 dataset.

Usage

Run python3 QANet_main.py --batch_size 32 --epochs 30 --with_cuda --use_ema to train model with cuda.

Run python3 QANet_main.py --batch_size 32 --epochs 3 --with_cuda --use_ema --debug to debug with small batches data.

Structure

QANet_main.py: driver program

trainer/QANet_trainer.py: trainer.

model/QANet_model.py: defines QANet.

data_loader/SQuAD.py: SQuAD 1.1 and 2.0 data loader.

Acknowledgement

  1. The QANet structure implementation is mainly based on https://github.com/BangLiu/QANet-PyTorch

  2. Baseline model is taken from https://github.com/chrischute/squad


上一篇：Chinese_QAnet

下一篇：qanet-unsupervised-faq-chatbot

用户评价
全部评价

热门资源

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • shih-styletransfer

    shih-styletransfer Code from Style Transfer ...