“NLP Status Report 2017-1-3”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
第20行: 第20行:
 
|-
 
|-
 
|Andi Zhang ||
 
|Andi Zhang ||
*coded to output encoder outputs and correspoding source & target sentences(ids in dictionaries)
+
*handed in previous codes to Mrs.Feng
*coded a script for bleu scoring, which tests the five checkpoints auto created by training process and save the one with best performance
+
*help Jiyuan gather poems about tianyuan
 
||
 
||
*
+
*help Jiyuan with his work
 +
*gather more poems
 
|-
 
|-
 
|Shiyue Zhang ||  
 
|Shiyue Zhang ||  

2017年1月3日 (二) 05:50的版本

Date People Last Week This Week
2016/12/26 Yang Feng
  • nmt+mn: tried to improve the nmt baseline;
  • read the code of Andy's;
  • wrote the code for bleu evaluation;
  • finished the code of nmt+mn;
  • ran experiments;
Jiyuan Zhang
  • integrated tone_model to attention_model for insteading manul rule,but the effect wasn't good
  • replacing all_pz rule with half_pz
  • token a classical Chinese as input,generated poem [1]
  • 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
  • tried to add true action info when training gate, which got better results than no true actions, but still not very good.
  • tried different scale vectors, and found setting >=-5000 is good
  • tried to change cos to only inner product, and inner product is better than cos.
  • [report]
  • read 3 papers [[2]] [[3]] [[4]]
  • trying the joint training, which got a problem of optimization.
  • try the joint training
  • read more papers and write a summary
Guli
  • finished the first draft of the survey
  • voice tagging
  • morpheme-based nmt
  • improve nmt with monolingual data
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