“NLP Status Report 2017-5-22”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
第2行： 第2行：
 
!Date !! People !! Last Week !! This Week
 
!Date !! People !! Last Week !! This Week
 
|-
 
|-
−
| rowspan="6"|2017/4/5
+
| rowspan="6"|2017/5/22
 
|Jiyuan Zhang ||
 
|Jiyuan Zhang ||
 
||  
 
||  

2017年5月24日 (三) 01:54的版本

Date People Last Week This Week
2017/5/22 Jiyuan Zhang
Aodong LI
Shiyue Zhang
  • tried to not train embedding but use external word vectors
  • most results of my attempts are bad, only 3-layer rnn + no dropout model got 25.54 bleu which about 2 points worse than original baseline
  • trained original baseline on new data ( the data fixed the reverse sentence problem), got bleu=27.88; moses bleu=32.47
  • try more models to get similar results as original baseline on new data
  • m-nmt model on new data
Shipan Ren
  • learn the implement of seq2seq model
  • read tf_translate code
  • understand the meaning of main code
  • start writing documents
取自“http://index.cslt.org/mediawiki/index.php?title=NLP_Status_Report_2017-5-22&oldid=27201”