“Huilian-cslt-week-2015-12-10”版本间的差异
来自cslt Wiki
（以“==Environment== * buy a DELL K40 server done * configure the system ==RNN Poem Processing== * attention training from Renmin newspaper done --Qixin Wang done * ch...”为内容创建页面） |
|||
| 第1行： | 第1行： | ||
==Environment== | ==Environment== | ||
| − | * buy a DELL K40 server done | + | * buy a 12G DELL K40 server done |
| − | * configure the system | + | * configure the system done |
==RNN Poem Processing== | ==RNN Poem Processing== | ||
* attention training from Renmin newspaper done --Qixin Wang done | * attention training from Renmin newspaper done --Qixin Wang done | ||
* change corpus done | * change corpus done | ||
| − | * contact specialists of Song Peams | + | * contact specialists of Song Peams done |
* write a patent done | * write a patent done | ||
* submit a patent --Xinkai | * submit a patent --Xinkai | ||
| − | * demo release(unified model) | + | * demo release(unified model) done |
| + | * add to language model information | ||
==RNN Writing Processing== | ==RNN Writing Processing== | ||
* write code done -- Chao Xing | * write code done -- Chao Xing | ||
| − | * generate Xing style using variational RNN | + | * generate Xing style using variational RNN |
==RNN QA== | ==RNN QA== | ||
* rnn rescore | * rnn rescore | ||
| − | :* rnn rescore should be used as a factor for learning | + | :* rnn rescore should be used as a factor for learning to rank |
* similar question --Bingdong | * similar question --Bingdong | ||
| − | * | + | * Huilan test -- Tianyi Luo(12.17) |
==Couplet== | ==Couplet== | ||
* attention training done --Tianyi Luo | * attention training done --Tianyi Luo | ||
| − | * focused attending training(12. | + | * focused attending training(12.17) |
| − | * revise training | + | * revise training corpus（12.17） |
2015年12月10日 (四) 02:10的最后版本
Environment
- buy a 12G DELL K40 server done
- configure the system done
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
- demo release(unified model) done
- add to language model information
RNN Writing Processing
- write code done -- Chao Xing
- generate Xing style using variational RNN
RNN QA
- rnn rescore
- rnn rescore should be used as a factor for learning to rank
- similar question --Bingdong
- Huilan test -- Tianyi Luo(12.17)
Couplet
- attention training done --Tianyi Luo
- focused attending training(12.17)
- revise training corpus（12.17）
