[Adapt] paragraph-based question generation

[kelsey]

Hi, adapters,


Today I'm going to introduce the paper published in EMNLP18 "Paragraph-level Neural Question Generation
with Maxout Pointer and Gated Self-attention Networks". In this paper, the authors addressed the problem that LSTM will forget something when the paragraph is too long, and they also addressed the sequence repetition problem with "Maxout Pointer".


Kelsey


Paper link: http://aclweb.org/anthology/D18-1424
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20190227/20bccf28/attachment.html>