“Huilian-cslt-week-2016-4-7”版本间的差异
来自cslt Wiki
（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） |
|||
| 第1行： | 第1行： | ||
==Environment== | ==Environment== | ||
| − | + | ||
==RNN Poem Processing== | ==RNN Poem Processing== | ||
| − | |||
* Theme training --valid set converge | * Theme training --valid set converge | ||
:* segment word | :* segment word | ||
| − | :* optimize speed | + | :* optimize speed done |
| − | * automatic | + | * automatic music generation --Jiyuan |
| − | :* | + | :* 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)-- | + | * attention based QA (Solution for template expansion)--Tianyi |
| − | :* train chatting model | + | :* 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 | ||
2016年4月7日 (四) 01:48的版本
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
