Pytorch implementation of machine comprehension papers for SQuAD v1.1
BIDAF (Minjoon Seo et al.,2016) https://arxiv.org/abs/1611.01603
QANet (Adams Wei Yu et al.,2018) https://arxiv.org/abs/1804.09541
Ensemble model for BIDAF and QANet
- preproc.py: dataset preprocessing and build training features
- config.py: determine which model to train and hype-parameters setting
- evaluate.py: evaluate script
- main.py: program entry
- models/qanet.py: QANet model
- models/bidaf.py: BIDAF model
- models/ensemble.py QANet and BIDAF ensemble
Result on dev dataset
| QANet | BIDAF | Ensemble | |
|---|---|---|---|
| F1 | 76.3 | 74.1 | 77.6 |
| EM | 67.5 | 63.3 | 68 |
- Context length is set to 300 due to limit of memory
- Char embedding doesn't be connected with convolution layer
- Difference hype parameters setting
- Achieve the result in paper
- Reduce memory cost
- Complete R-net model
- Do the ensemble