- A Tensorflow implementation of Hierarchical Attention Flow for Multiple-Choice Reading Comprehension.
- Specially designed for oqmrc(password:duco) dataset.
- Project is based on a R-Net implementation.
- Python = 3.6.0
- Tensorflow-gpu = 1.5.0
- spaCy >= 2.0.0
- tqdm
Download dataset from oqmrc(password:duco), and unzip downloaded files.Remember to modify your data path before training.
- A pre-training word vector is required, for Chinese word vectors you can refer to here.
- We utilized Zhihu_QA word vectors in our experiments.
python config --mode prepro
python config --mode train
python config --mode test
Single-model accuracy on dev set is 0.7287.