LSTM-based model for answer selection
This project is based on LSTM-based Deep Learning Models for Non-factoid Answer Selection. The dataset used is from Microsoft Beauty of Programming 2017. The word vector used is from https://github.com/Embedding/Chinese-Word-Vectors (Wikipedia_zh 中文维基百科 SGNS word). Download link: https://pan.baidu.com/s/1AmXYWVgkxrG4GokevPtNgA.
The project achieved arround 52% MRR(Mean Reciprocal Rank) on the validation set.