“Huilian-cslt-week-2015-12-31”版本间的差异
来自cslt Wiki
(以“==Environment== * buy a 12G DELL K40 server done * configure the system done ==RNN Poem Processing== * attention training from Renmin newspaper done --Qixin Wang do...”为内容创建页面) |
|||
(2位用户的2个中间修订版本未显示) | |||
第1行: | 第1行: | ||
==Environment== | ==Environment== | ||
− | + | ||
− | + | ||
==RNN Poem Processing== | ==RNN Poem Processing== | ||
第11行: | 第10行: | ||
* demo release(unified model) done | * demo release(unified model) done | ||
* add to language model information | * add to language model information | ||
+ | * crowdsourcing platform check | ||
==RNN Writing Processing== | ==RNN Writing Processing== | ||
第16行: | 第16行: | ||
* generate Xing style using variational RNN | * generate Xing style using variational RNN | ||
:* use mnist dataset done | :* use mnist dataset done | ||
− | :* train using chinese dataset | + | :* train using chinese dataset done |
* train reference to the paper of BAYESIAN PROBABILISTIC PROGRAM FOR IMAGE GENERATION | * train reference to the paper of BAYESIAN PROBABILISTIC PROGRAM FOR IMAGE GENERATION | ||
第23行: | 第23行: | ||
:* rnn rescore should be used as a factor for learning to rank | :* rnn rescore should be used as a factor for learning to rank | ||
* similar question --Bingdong | * similar question --Bingdong | ||
− | * Huilan test -- | + | ** Huilan test -- Bingdong |
− | * train corpus of word vector--hulian | + | *** train corpus of word vector--hulian |
− | * add traditional method of learning to rank--Tianyi | + | *** add traditional method of learning to rank--Tianyi |
* memory machine(about three months)--Tianyi | * memory machine(about three months)--Tianyi | ||
− | |||
==Couplet== | ==Couplet== | ||
* attention training done --Tianyi Luo | * attention training done --Tianyi Luo | ||
− | * focused attending training | + | * focused attending training |
− | * revise training | + | * revise training corpus |
2016年1月4日 (一) 02:33的最后版本
Environment
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(1.15)
- demo release(unified model) done
- add to language model information
- crowdsourcing platform check
RNN Writing Processing
- write code done -- Chao Xing
- generate Xing style using variational RNN
- use mnist dataset done
- train using chinese dataset done
- train reference to the paper of BAYESIAN PROBABILISTIC PROGRAM FOR IMAGE GENERATION
RNN QA
- rnn rescore
- rnn rescore should be used as a factor for learning to rank
- similar question --Bingdong
- Huilan test -- Bingdong
- train corpus of word vector--hulian
- add traditional method of learning to rank--Tianyi
- Huilan test -- Bingdong
- memory machine(about three months)--Tianyi
Couplet
- attention training done --Tianyi Luo
- focused attending training
- revise training corpus