“NLP Status Report 2017-5-31”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
第34行： 第34行：
 
* m-nmt is running
 
* m-nmt is running
 
||
 
||
−
 
+
* get word2vec on big data, and compare with word2vec from train data
 +
* test m-nmt model, increase vocab size and test
 +
* review zh-uy/uy-zh related works, start to write paper
 
|-
 
|-
 
|Shipan Ren ||
 
|Shipan Ren ||

2017年5月31日 (三) 04:21的版本

Date People Last Week This Week
2017/5/22 Jiyuan Zhang
Aodong LI
Shiyue Zhang
  • found dropout bug, fix it, and reran baseline: baseline 35.21, baseline(outproj=emb) 35.24
  • tried several embed set models, failed
  • embedded other words to model embedding space (trained on train data not big data), and then directly used in baseline(outproj=emb)
30000 50000 70000 90000
35.24 34.52 33.73 33.16
4564 (6666) 4535 4469 4426
  • m-nmt is running
  • get word2vec on big data, and compare with word2vec from train data
  • test m-nmt model, increase vocab size and test
  • review zh-uy/uy-zh related works, start to write paper
Shipan Ren
取自“http://index.cslt.org/mediawiki/index.php?title=NLP_Status_Report_2017-5-31&oldid=27238”