Huilian-cslt-week-2016-1-14 - 版本历史

2016年1月14日 (四) 02:22 Zxw

2016-01-14T02:22:11Z

2016年1月14日 (四) 01:56 Zxw

2016-01-14T01:56:46Z

Zxw：以“==Environment== ==RNN Poem Processing== * attention training from Renmin newspaper done --Qixin Wang done * change corpus done * contact specialists of Song Pe...”为内容创建页面

2016-01-14T01:28:10Z

以“==Environment== ==RNN Poem Processing== * attention training from Renmin newspaper done --Qixin Wang done * change corpus done * contact specialists of Song Pe...”为内容创建页面

新页面

==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
* memory machine(about three months)--Tianyi

==Couplet==
* attention training done --Tianyi Luo
* focused attending training
* revise training corpus

@@ 第22行： / 第22行： @@
 ==RNN QA==
-* rnn rescore
+* rnn rescore--Bingdong
 :* rnn rescore should be used as a factor for learning to rank
-* similar question --Bingdong
+* query expansion--Bingdong
-** Huilan test -- Bingdong
+* attention based QA (Solution for template expansion)--Dongxu
-*** train corpus of word vector--hulian
+* attention and memory QA(2016.2-2016.4)--Tianyi
-*** add traditional method of learning to rank--Tianyi
-* memory machine(about three months)--Tianyi
 ==Couplet==
-* attention training done --Tianyi Luo
+* smt training
-* focused attending training
+:*corpus expansion
 * revise training corpus

@@ 第7行： / 第7行： @@
 * contact  specialists of Song Peams done
 * write a patent   done
-* submit a patent --Xinkai(1.15)
+* submit a patent done
 * demo release(unified model) done
 * add to language model information
-* crowdsourcing platform check
+* contact specialists
 ==RNN Writing Processing==
@@ 第18行： / 第19行： @@
 :* train using chinese dataset done
 * train reference to the paper of BAYESIAN PROBABILISTIC PROGRAM FOR IMAGE GENERATION
 ==RNN QA==