“Huilian-cslt-week-2015-12-31”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
(以“==Environment== * buy a 12G DELL K40 server done * configure the system done ==RNN Poem Processing== * attention training from Renmin newspaper done --Qixin Wang do...”为内容创建页面)
 
 
(2位用户的2个中间修订版本未显示)
第1行: 第1行:
 
==Environment==
 
==Environment==
* buy a 12G DELL K40 server done
+
 
* configure the system done
+
  
 
==RNN Poem Processing==
 
==RNN Poem Processing==
第11行: 第10行:
 
* demo release(unified model) done
 
* demo release(unified model) done
 
* add to language model information
 
* add to language model information
 +
* crowdsourcing platform check 
  
 
==RNN Writing Processing==
 
==RNN Writing Processing==
第16行: 第16行:
 
* generate Xing style using variational RNN   
 
* generate Xing style using variational RNN   
 
:* use mnist dataset done
 
:* use mnist dataset done
:* train using chinese dataset
+
:* train using chinese dataset done
 
* train reference to the paper of BAYESIAN PROBABILISTIC PROGRAM FOR IMAGE GENERATION  
 
* train reference to the paper of BAYESIAN PROBABILISTIC PROGRAM FOR IMAGE GENERATION  
  
第23行: 第23行:
 
:* rnn rescore should be used as a factor for learning to rank  
 
:* rnn rescore should be used as a factor for learning to rank  
 
* similar question --Bingdong
 
* similar question --Bingdong
* Huilan test -- Tianyi Luo(12.17)
+
** Huilan test -- Bingdong
* train corpus of word vector--hulian
+
*** train corpus of word vector--hulian
* add traditional method of learning to rank--Tianyi
+
*** add traditional method of learning to rank--Tianyi
 
* memory machine(about three months)--Tianyi
 
* memory machine(about three months)--Tianyi
 
  
 
==Couplet==
 
==Couplet==
 
* attention training done --Tianyi Luo
 
* attention training done --Tianyi Luo
* focused attending training(12.17)
+
* focused attending training
* revise training corpus(12.17)
+
* revise training corpus

2016年1月4日 (一) 02:33的最后版本

Environment

RNN Poem Processing

  • attention training from Renmin newspaper done --Qixin Wang done
  • change corpus done
  • contact specialists of Song Peams done
  • write a patent done
  • submit a patent --Xinkai(1.15)
  • demo release(unified model) done
  • add to language model information
  • crowdsourcing platform check

RNN Writing Processing

  • write code done -- Chao Xing
  • generate Xing style using variational RNN
  • use mnist dataset done
  • train using chinese dataset done
  • train reference to the paper of BAYESIAN PROBABILISTIC PROGRAM FOR IMAGE GENERATION

RNN QA

  • rnn rescore
  • rnn rescore should be used as a factor for learning to rank
  • similar question --Bingdong
    • Huilan test -- Bingdong
      • train corpus of word vector--hulian
      • add traditional method of learning to rank--Tianyi
  • memory machine(about three months)--Tianyi

Couplet

  • attention training done --Tianyi Luo
  • focused attending training
  • revise training corpus