Difference between revisions of "NLP Status Report 2017-1-10"

From cslt Wiki
Jump to: navigation, search
(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)
 
 
(7 intermediate revisions by 4 users not shown)
Line 4: Line 4:
 
| rowspan="6"|2017/1/3
 
| rowspan="6"|2017/1/3
 
|Yang Feng ||
 
|Yang Feng ||
*[[nmt+mn:]] tried to improve the nmt baseline;
+
*[[nmt+mn:]] fixed the problem of generating unreasonable results of baselines;
*met with problems for baseline, rulling out the factor of output order and file format and got the reason of learning rate.
+
* ran experiments [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Nmt_mn_report.pdf report]];
*read the code of Andy's;
+
* polished and submitted the TRP of Moses;
*wrote the code for bleu evaluation;
+
* wrote the code of result analysis (under-going);
*managed to fix the code of nmt+mn;
+
*ran experiments [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Nmt_mn_report.pdf report]]
+
 
||
 
||
*[[nmt+mn:]] do further experiments.
+
*[[nmt+mn:]] analyze results;
 +
*do more experiments
 
|-
 
|-
 
|Jiyuan Zhang ||
 
|Jiyuan Zhang ||
*improved speed of prediction process
+
*designed the questionnaire, then discovered some problems and redesigned
*ran expriments:<br/>
+
two sytles expriments of top1_memory_model<br/>
+
overfitting expriments of top1_memory_model<br/>
+
two styles expriments of average_memory_model<br/>
+
overfitting expirments of average_memory_model
+
 
||  
 
||  
*improve poem model  
+
*complete the questionnaire  
 
|-
 
|-
 
|Andi Zhang ||
 
|Andi Zhang ||
*handed in previous codes to Mrs.Feng
+
*helped Jiyuan dealing with poem questionnaires
*help Jiyuan gather poems about tianyuan
+
 
||
 
||
*help Jiyuan with his work
+
*continue this work, may start collecting feedback if all questionnaires are filled out
*gather more poems
+
 
|-
 
|-
 
|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 ||

Latest revision as of 04:51, 16 January 2017

Date People Last Week This Week
2017/1/3 Yang Feng
  • nmt+mn: fixed the problem of generating unreasonable results of baselines;
  • ran experiments [report];
  • polished and submitted the TRP of Moses;
  • wrote the code of result analysis (under-going);
  • nmt+mn: analyze results;
  • do more experiments
Jiyuan Zhang
  • designed the questionnaire, then discovered some problems and redesigned
  • complete the questionnaire
Andi Zhang
  • helped Jiyuan dealing with poem questionnaires
  • continue this work, may start collecting feedback if all questionnaires are filled out
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