[Adapt] [Seminar] A Grammar-Based Structural CNN Decoder for Code Generation

[Yang Li]

Dear Adapters,

          This week, I will give an introduction about the paper “A Grammar-Based Structural CNN Decoder for Code Generation” which is accepted by AAAI in 2019. This paper proposes a grammar-based structural CNN for code generation. The model generates a program by predicting the grammar rules of the programming language; authors design several CNN modules, including the tree-based convolution and pre-order convolution, whose information is further aggregated by dedicated attentive pooling layers.


Wed 5:00pm
SEIEE 3-414


Best,
YangLi


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20190529/95a57db0/attachment.html>