“NLP Status Report 2017-7-24”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
(以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/7/3 |Jiyuan Zhang || * || *make the poster for ACL *complete neural model for t...”为内容创建页面)
 
第21行: 第21行:
 
|-
 
|-
 
|Shipan Ren ||
 
|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
 
*train two versions of the code on WMT2014 en-de and en-fr datasets
  tested these checkpoints of en-de dataset
+
  under training
 +
  new version saved more time
 +
 
 +
*read paper(memory-augmented-nmt and Memory augmented Chinese-Uyghur Neural Machine Translation) 
  
 
||
 
||
* tested these checkpoints of en-fr dataset
+
* read memory-augmented-nmt code
* record the result and do analysis
+
 
* read papers about memory augmented NMT  
 
* read papers about memory augmented NMT  
 
|-
 
|-

2017年7月26日 (三) 03:40的版本

Date People Last Week This Week
2017/7/3 Jiyuan Zhang
  • make the poster for ACL
  • complete neural model for the couplet
Aodong LI
Shiyue Zhang
Shipan Ren
  • train two versions of the code on WMT2014 en-de and en-fr datasets
 under training 
 new version saved more time
  • read paper(memory-augmented-nmt and Memory augmented Chinese-Uyghur Neural Machine Translation)
  • read memory-augmented-nmt code
  • read papers about memory augmented NMT