search

localminimum / QANet

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

Results of the original paper #19

Closed yizhongw closed 6 years ago

yizhongw commented 6 years ago

Thanks for this great implementation. I noticed that you mentioned in the README file that the original system can achieve EM: 72.5, F1: 81.4 after 150,000 training steps, and EM: 76.2, F1: 84.6 after 340,000 training steps. But I didn't find this information in the original paper. It seems that the original system takes much longer time to train? Could you show me where to get this information? Or did you infer that from other statistics?

localminimum commented 6 years ago

Hi @EastonWang , there has been a revision in the paper since I wrote down that statistics. You can find the results by the authors from the original paper. Check subsection 4.1.2. I will update the readme now. Thanks.