“NLP Status Report 2017-9-4”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
第17行: 第17行:
  
 
||
 
||
 
 
|-
 
|-
 
|Shipan Ren  
 
|Shipan Ren  
 
||   
 
||   
* read the released information of other toolkits for nmt
+
* checked experimental results and found some few small problems,like follows:
* cleaned up the code
+
    sentence before tokenize:
* wrote the documents [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/5c/Manual_V1.0.docx] [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/38/Manual_V0.10.docx]
+
    "If no more people smoked, this rate would increase to at least 50%," says André Beaulieu,
 +
    spokesman for the Canadian Cancer Society.
 +
    sentence after tokenize:
 +
    " if no more people smoked , this rate would increase to at least 50 % , " says andré beaulieu ,
 +
    spokesman for the canadian cancer society .
 +
    It is just a equivalent replacement
 +
* wrote the first draft paper of ViVi_NMT 
 +
* pushed the baseline code,readme file and user manual to cslt github(https://github.com/CSLT-THU/CSLT_NMT)
 
||   
 
||   
* write the papers of our baseline system
+
* read some translating phrases papers
* read augmented nmt code
+
* learn more about the memory mechanism
 
|-
 
|-
  

2017年9月4日 (一) 01:52的版本

Date People Last Week This Week
2017/8/14 Jiyuan Zhang
  • code refactoring
  • wrote a document[1]
Aodong LI
Shiyue Zhang
Shipan Ren
  • checked experimental results and found some few small problems,like follows:
   sentence before tokenize:
   "If no more people smoked, this rate would increase to at least 50%," says André Beaulieu, 
   spokesman for the Canadian Cancer Society.
   sentence after tokenize:
   " if no more people smoked , this rate would increase to at least 50 % , " says andré beaulieu , 
   spokesman for the canadian cancer society .
   It is just a equivalent replacement
  • read some translating phrases papers
  • learn more about the memory mechanism
Jiayu Guo
  • Clean up the code of predict.py
  • configuration environment of TF-0.12 or update the code to adapt TF-1.0