Repository files navigation

Question-Answering is a classical problem in natural language processing, which aims at designing systems that can automatically answer a question, in the same way as human does.

In this repo, I implemented end-to-end neural networks model which aims to answer questions from a given passage.

HUMAN PERFORMANCE

• EM: 86.831
• F1: 89.452

• DrQA
• BiDAF
• QANet
• RNet

• [0] Chen, D., Bolton, J., & Manning, C. D. (2016). A thorough examination of the cnn/daily mail reading comprehension task. arXiv preprint arXiv:1606.02858.
• [1] Chen, D., Fisch, A., Weston, J., & Bordes, A. (2017). Reading wikipedia to answer open-domain questions. arXiv preprint arXiv:1704.00051.