“Huilian-cslt-week-2015-12-31”版本间的差异
来自cslt Wiki
| 第4行： | 第4行： | ||
==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 done | * contact specialists of Song Peams done | ||
* write a patent done | * write a patent done | ||
2016年1月4日 (一) 02:31的版本
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
- corpus is ready
- add traditional method of learning to rank--Tianyi
- memory machine(about three months)--Tianyi
Couplet
- attention training done --Tianyi Luo
- focused attending training
- revise training corpus
