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

From cslt Wiki
Jump to: navigation, search
Line 4: Line 4:
 
| rowspan="6"|2017/1/3
 
| rowspan="6"|2017/1/3
 
|Yang Feng ||
 
|Yang Feng ||
*[[nmt+mn:]] fixed the problem of generating unreasonable results of baselines;
+
* [[nmt+mn:]] ran experiments with only 3-entry memory to check the impact of memory;
* ran experiments [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Nmt_mn_report.pdf report]];
+
* check the translations and also ran experiments to analyze the results [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/07/Nmt_mn_result_summary.xlsx translation]] [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Nmt_mn_report.pdf report]];
* polished and submitted the TRP of Moses;
+
* add c_i and y_i-1 to improve the fluency;
* wrote the code of result analysis (under-going);
+
* fix a bug of baseline of using different embedding for forward and backward rnns (under-running);
 
||
 
||
*[[nmt+mn:]] analyze results;
+
*[[nmt+mn:]] *do more experiments
*use the embedding of word2vec;
+
*do more experiments
+
 
|-
 
|-
 
|Jiyuan Zhang ||
 
|Jiyuan Zhang ||

Revision as of 04:49, 16 January 2017

Date People Last Week This Week
2017/1/3 Yang Feng
  • nmt+mn: ran experiments with only 3-entry memory to check the impact of memory;
  • check the translations and also ran experiments to analyze the results [translation] [report];
  • add c_i and y_i-1 to improve the fluency;
  • fix a bug of baseline of using different embedding for forward and backward rnns (under-running);
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