Question and Answering Language Model
Convolutional Neural Network for Chinese InsuranceQA Corpus with TensorFlow, implementation of paper "Applying Deep Learning to Answer Selection: A Study and An Open Task".
- py2
- TensorFlow v1.0+
pip install -r Requirements.txt
python2 train.py
Customize the hyper parameters: python2 train.py --help
scripts/start_tensorboard.sh
open http://localhost:6006
在默认参数下，运行57,123 steps: loss 0.591968, acc 0.8
https://github.com/l11x0m7/InsuranceQA_zh/wiki
-
网络设计
-
数据设计
-
调优过程
-
结果
-
参考文献