“NLP Status Report 2017-1-10”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"|2017/1/3 |Yang Feng || *nmt+mn: tried to improve the nmt baseline; *met with prob...”为内容创建页面)
 
第31行: 第31行:
 
|-
 
|-
 
|Shiyue Zhang ||  
 
|Shiyue Zhang ||  
* tried to improve rnng+mm model, but still failed  [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/9f/RNNG%2Bmm_experiment_report.pdf report]]
+
* finished running theano baseline
* stopped rnng work to help Teacher Feng with NMT
+
* read and understood the beam search in theano baseline
* ran theano NMT code successfully, and found a problem of test
+
* started to write the [http://dynet-doc-zh.readthedocs.io/zh_CN/latest/ Dynet Chinese Document]
 +
* started to implement beam search to tensorflow baseline
 
||
 
||
* run and test the theano NMT model
+
* finished the beam search implementation
* try to modify tensorflow NMT model, run and test
+
* go on with Dynet Chinese Document
 
|-
 
|-
 
|Guli ||
 
|Guli ||

2017年1月10日 (二) 05:28的版本

Date People Last Week This Week
2017/1/3 Yang Feng
  • nmt+mn: tried to improve the nmt baseline;
  • met with problems for baseline, rulling out the factor of output order and file format and got the reason of learning rate.
  • read the code of Andy's;
  • wrote the code for bleu evaluation;
  • managed to fix the code of nmt+mn;
  • ran experiments [report]
Jiyuan Zhang
  • improved speed of prediction process
  • ran expriments:

two sytles expriments of top1_memory_model
overfitting expriments of top1_memory_model
two styles expriments of average_memory_model
overfitting expirments of average_memory_model

  • improve poem model
Andi Zhang
  • handed in previous codes to Mrs.Feng
  • help Jiyuan gather poems about tianyuan
  • help Jiyuan with his work
  • gather more poems
Shiyue Zhang
  • finished running theano baseline
  • read and understood the beam search in theano baseline
  • started to write the Dynet Chinese Document
  • started to implement beam search to tensorflow baseline
  • finished the beam search implementation
  • go on with Dynet Chinese Document
Guli
  • run nmt with monolingual data
  • bleu computation
  • learn about tensorflow
  • improve my paper
  • analyze experiment results
Peilun Xiao
  • learned tf-idf algorithm
  • coded tf-idf alogrithm in python,but found it not worked well
  • tried to use small dataset to test the program
  • use sklearn tfidf to test the dataset