Invertigation of BiDAF and implementation of QANet for Question Answering

img
In this project, I build two question answering system that have relatively good performance on SQuAD 2.0 dataset. The baseline model is Bi-Directional Attention Flow (BiDAF), which achieved 59.21 F1, 55.92 EM and 65.85 AvNA on Dev dataset. Firstly I implement a CNN-based character embedding to it which achieved 60.192 EM, 63.480 F1 on Dev dataset. Then I re-implement QANet with Pytorch which is basically the same as the original paper proposed one. It achieved 59.973 EM, 63.403 F1 on Dev dataset, which is less than the first one. Ultimately, I got 59.307 EM and 62.761 F1 on test set.