“NLP Status Report 2017-7-17”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
第6行: 第6行:
 
*
 
*
 
||  
 
||  
*
+
*generate streame according to a couplet 
 +
*try my best to complete the task of filling in the blanks of a couplet
 
|-
 
|-
 
|Aodong LI ||
 
|Aodong LI ||

2017年7月18日 (二) 04:32的版本

Date People Last Week This Week
2017/7/3 Jiyuan Zhang
  • generate streame according to a couplet
  • try my best to complete the task of filling in the blanks of a couplet
Aodong LI
Shiyue Zhang
Shipan Ren
  • found ways to tokenize the WMT2014 data
  rewrote prepare_data.py form moses-smt
  used the tokenizer of moses-smt
  • train two versions of the code on WMT2014 en-de and en-fr datasets
  tested these checkpoints of en-de dataset
  • tested these checkpoints of en-fr dataset
  • record the result and do analysis
  • read papers about memory augmented NMT