“Huilian-cslt-week-2016-2-18”版本间的差异

2016年2月18日 (四) 02:28的最后版本

Environment

RNN Poem Processing

• contact specialists --Qixin done
• speed up training(minibath parallel) done
• update a new version

RNN Writing Processing

• neural model learnig transform --Xingchao
• BPL speed up (transform first,then do this)

RNN QA

• attention based QA (Solution for template expansion)--Dongxu

• make sure whether the model is correct using the standard corpus
• train word vector
• initial model

• attention and memory QA(2016.2-2016.4)--Tianyi
• Dongxu Investigation first

• rnn rescore--Bingdong

• rnn rescore should be used as a factor for learning to rank

• query expansion--Bingdong

Couplet

• bug fits