“NLP Status Report 2016-12-19”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
第28行： 第28行：
 
|-
 
|-
 
|Shiyue Zhang ||  
 
|Shiyue Zhang ||  
−
* finished tsne pictures, and discussed with teachers
+
* changed the one-hot vector to (0, -inf, -inf...), and retied the experiments. But no improvement showed.
−
* tried experiments with 28-dim mem, but found almost all of them converged to baseline
+
* tried 1-dim gate, but converged to baseline
−
* returned to 384-dim mem, which is still slightly better than basline.
+
* tried to only train gate, but the best is taking all instance as "right"
−
* found the problem of action mem, one-hot vector is not proper.
+
* trying a model similar to attention
 
* [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/2f/RNNG%2Bmm%E5%AE%9E%E9%AA%8C%E6%8A%A5%E5%91%8A.pdf report]]
 
* [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/2f/RNNG%2Bmm%E5%AE%9E%E9%AA%8C%E6%8A%A5%E5%91%8A.pdf report]]
 
||
 
||

2016年12月19日 (一) 05:19的版本

Date People Last Week This Week
2016/12/12 Yang Feng
  • s2smn: wrote the manual of s2s with tensorflow [nmt-manual]
  • wrote part of the code of mn.
  • wrote the manual of Moses [moses-manual]
  • Huilan: fixed the problem of syntax-based translation.
  • sort out the system and corresponding documents.
Jiyuan Zhang
  • attempted to use memory model to improve the atten model of bad effect
  • With the vernacular as the input，generated poem by local atten model[1]
  • Modified working mechanism of memory model(top1 to average)
  • help andi
  • improve poem model
Andi Zhang
  • prepared a paraphrase data set that is enumerated from a previous one (ignoring words like "啊呀哈")
  • worked on coding bidirectional model under tensorflow, met with NAN problem
  • ignore NAN problem for now, run it on the same data set used in Theano
Shiyue Zhang
  • changed the one-hot vector to (0, -inf, -inf...), and retied the experiments. But no improvement showed.
  • tried 1-dim gate, but converged to baseline
  • tried to only train gate, but the best is taking all instance as "right"
  • trying a model similar to attention
  • [report]
  • change one-hot vector to (0, -10000.0, -10000.0...)
  • try 1-dim gate
  • try max cos
Guli
  • install and run moses
  • prepare thesis report
  • read papers about Transfer learning and solving OOV
Peilun Xiao
  • Read a paper about document classification wiht GMM distributions of word vecotrs and try to code it in python
  • Use LDA to reduce the dimension of the text in r52、r8 and contrast the performance of classification
  • Use LDA to reduce the dimension of the text in 20news and webkb
取自“http://index.cslt.org/mediawiki/index.php?title=NLP_Status_Report_2016-12-19&oldid=24848”