localminimum / QANet

A Tensorflow implementation of QANet for machine reading comprehension
MIT License
983 stars 305 forks source link

This repo cannot reproduce the result of original paper #49

Open DC-Swind opened 5 years ago

DC-Swind commented 5 years ago

Thank you for your implementation, it is very helpful for me. I run this code and can get the similar result when the number of heads equals to 1. But, I cannot get the result of original paper(73.6/82.7) when I use 8 heads, batch size 32, training step 150k, char dimension of 200 (the same setting as the original paper). I can only get around (71.27/80.58). Same situation was ocurred when I ran the pytorch repo (https://github.com/andy840314/QANet-pytorch-).

Any suggestions?

JACKHAHA363 commented 5 years ago

Have you been able to reproduce the original paper's result?

DC-Swind commented 5 years ago

I tried my best, but the result was still two points below.