Difference between revisions of "Huilian-cslt-week-2016-5-26"

From cslt Wiki
Jump to: navigation, search
(以“==Environment== ==RNN Poem Processing== * Theme training --valid set converge :* segment word :* optimize speed done :* theme poem generation ==RNN Writing Pr...”为内容创建页面)
 
 
Line 6: Line 6:
 
:* segment word
 
:* segment word
 
:* optimize speed done
 
:* optimize speed done
:* theme poem generation
+
:* theme poem generation  
  
 
==RNN Writing Processing==
 
==RNN Writing Processing==
* hold
+
* neural model learning transform --Xingchao,Yanxu
* neural model learning transform --Xingchao
+
 
:* add attention  
 
:* add attention  
 
:* use tensor flow
 
:* use tensor flow
* BPL --Yanxu
+
:* LSTM --Yanxu
  
 
==RNN QA(release in June)==
 
==RNN QA(release in June)==
* attention based QA (Solution for template expansion)--Tianyi
+
* attention based QA (Solution for template expansion)
:* collect Simsimi corpus --Bingdong
+
* train chatting model  
::* train chatting model  
+
* CDSSM vector --Xingchao
* RNN vector without attention  --Tianyi
+
* attention and memory QA
:* DSSM vector --Xingchao
+
:* hold
:* compare to DSSM vector
+
:* attention and memory QA
+

Latest revision as of 01:55, 26 May 2016

Environment

RNN Poem Processing

  • Theme training --valid set converge
  • segment word
  • optimize speed done
  • theme poem generation

RNN Writing Processing

  • neural model learning transform --Xingchao,Yanxu
  • add attention
  • use tensor flow
  • LSTM --Yanxu

RNN QA(release in June)

  • attention based QA (Solution for template expansion)
  • train chatting model
  • CDSSM vector --Xingchao
  • attention and memory QA
  • hold