Difference between revisions of "Huilian-cslt-week-2016-4-7"

From cslt Wiki
Jump to: navigation, search
(以“==Environment== * hold ==RNN Poem Processing== * revise patent done * Theme training --valid set converge :* segment word :* optimize speed * automatic song ge...”为内容创建页面)
 
Line 1: Line 1:
 
==Environment==
 
==Environment==
* hold
+
 
  
 
==RNN Poem Processing==   
 
==RNN Poem Processing==   
* revise patent done
 
 
* Theme training --valid set converge  
 
* Theme training --valid set converge  
 
:* segment word
 
:* segment word
:* optimize speed
+
:* optimize speed done
* automatic song generation
+
* automatic music generation --Jiyuan
:* hold
+
:* generate piano
 +
:* generate Chinese music(Lijun Deng)
  
 
==RNN Writing Processing==
 
==RNN Writing Processing==
 
* neural model learnig transform --Xingchao
 
* neural model learnig transform --Xingchao
:* add attention
+
:* add attention  
 +
:* use tensor flow
 
* BPL --Yanxu
 
* BPL --Yanxu
  
 
==RNN QA==
 
==RNN QA==
* attention based QA (Solution for template expansion)--Dongxu,Tianyi
+
* attention based QA (Solution for template expansion)--Tianyi
:* train chatting model using tensor flow(--Dongxu) or theano(--Qixin)
+
:* collect Simsimi corpus --Bingdong
* RNN vector --Tianyi
+
::* train chatting model  
 +
* RNN vector without attention  --Tianyi
 
:* compare to DSSM vector
 
:* compare to DSSM vector
 
:* attention and memory QA
 
:* attention and memory QA

Revision as of 01:48, 7 April 2016

Environment

RNN Poem Processing

  • Theme training --valid set converge
  • segment word
  • optimize speed done
  • automatic music generation --Jiyuan
  • generate piano
  • generate Chinese music(Lijun Deng)

RNN Writing Processing

  • neural model learnig transform --Xingchao
  • add attention
  • use tensor flow
  • BPL --Yanxu

RNN QA

  • attention based QA (Solution for template expansion)--Tianyi
  • collect Simsimi corpus --Bingdong
  • train chatting model
  • RNN vector without attention --Tianyi
  • compare to DSSM vector
  • attention and memory QA