“Huilian-cslt-week-2016-5-26”版本间的差异
来自cslt Wiki
（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） |
|||
| 第6行： | 第6行： | ||
:* segment word | :* segment word | ||
:* optimize speed done | :* optimize speed done | ||
| − | :* theme poem generation | + | :* theme poem generation |
==RNN Writing Processing== | ==RNN Writing Processing== | ||
| − | + | * neural model learning transform --Xingchao,Yanxu | |
| − | * neural model learning transform --Xingchao | + | |
:* add attention | :* add attention | ||
:* use tensor flow | :* use tensor flow | ||
| − | * | + | :* LSTM --Yanxu |
==RNN QA(release in June)== | ==RNN QA(release in June)== | ||
| − | * attention based QA (Solution for template expansion) | + | * attention based QA (Solution for template expansion) |
| − | + | * train chatting model | |
| − | + | * CDSSM vector --Xingchao | |
| − | * | + | * attention and memory QA |
| − | + | :* hold | |
| − | + | ||
| − | + | ||
2016年5月26日 (四) 01:55的最后版本
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
