Difference between revisions of "NLP Status Report 2016-11-21"

From cslt Wiki
Jump to: navigation, search
Line 16: Line 16:
 
|-
 
|-
 
|Jiyuan Zhang ||
 
|Jiyuan Zhang ||
 
+
*ran decoder-memory model, but the effect is not obvious
 +
*changed binding way of memory and atten models, can generate different style of poetry
 +
*cleanned up our code
 +
*wrote a techreport about poemGen
 +
*submitted two databases about poemGen and musicGen
 
||  
 
||  
 
+
*explored a variety of binding ways of memory and atten model
 
|-
 
|-
 
|Andi Zhang ||
 
|Andi Zhang ||

Revision as of 01:13, 21 November 2016

Date People Last Week This Week
2016/11/21 Yang Feng
 rnng+mn
  • ran experiments of rnng+mn [report]
  • used top-k for memory, under training
 sequence-to-sequence + mn
  • wrote the proposal
  • discussed the details of Andy
  Intern interview
  Huilan's work
Jiyuan Zhang
  • ran decoder-memory model, but the effect is not obvious
  • changed binding way of memory and atten models, can generate different style of poetry
  • cleanned up our code
  • wrote a techreport about poemGen
  • submitted two databases about poemGen and musicGen
  • explored a variety of binding ways of memory and atten model
Andi Zhang
  • prepare new data set for paraphrase, wiped out repetition & most of the noises
  • run NMT on fr-en data set and new paraphrase set
  • read through source code to find ways to modify it
  • helped Guli with running NMT on our server
  • decide to drop theano or not
  • start to work on codes
Shiyue Zhang
  • run rnng on MKL successfully, which can double or triple the speed.
  • rerun the original model and get the final result 92.32
  • rerun the wrong memory models, still running
  • implement the dynamic memory model and get the result 92.54 which is 0.22 better than baseline
  • try another structure of memory
  • try more different models and summary the results
  • publish the technical reports
Guli