chenghuige / rczoo Goto Github PK

The RCZoo project is a toolkit for reading comprehension model. It contains the PyTorch reimplement of multiple reading comprehension model.
All the models are trained and tested on the SQuAD v1.1 dataset, and reach the performance in origin papers.

python 3.5
Pytorch 0.4
tqdm

We train each model on train set for 40 epoch, and report the best performance on dev set.

• training
• performance
• predicting scripts
  some different in the Dropout Layer

• training
• performance
• predicting scripts
  The bi-attention in BiDAF does not work fin, and I introduce the co-attention in DCN paper. The final results is better than that in origin paper

• training
• performance
• predicting scripts

borrow from origin code

• training
• performance
• predicting scripts

• training
• performance
• predicting scripts

• training
• performance
• predicting scripts
  no elmo contextualized embedding

• training
• performance
• predicting scripts
  no CoVe embedding

• run sh download.sh to download the dataset and the glove embeddings.
• run sh train_xxx.sh to start the train process. Dring the train process, model will be evaluated on dev set each epoch.

some code are borrowed from DrQA, a cool project about reading comprehension.

TODO:

• Recognizing unanswerable question for SQuAD, add new type of loss function to accommodate unanswerable question
• Processing multiple passage reading comprehension. Related datasets include TriviaQA, SearchQA, QuasarT