“NLP Status Report 2016-09-26”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"|2016/09/26 |Yang Feng || *revised papers of Icassp *installed MemNN on the server an...”为内容创建页面）
 
 
（4位用户的11个中间修订版本未显示）
第4行： 第4行：
 
| rowspan="6"|2016/09/26
 
| rowspan="6"|2016/09/26
 
|Yang Feng ||
 
|Yang Feng ||
−
*revised papers of Icassp
+
*prepared the phrasal check of Huilan
−
*installed MemNN on the server and get the similar results on PennTreeBank data set to that in the paper
+
*prepared and discussed the main idea of next work
−
*read the code of rnng and installed it on the server (not succeed yet)
+
*learned Lua and Torch and read the code of MemNN
 +
*read the code of rnng
 
||
 
||
−
*manage to install rnng on the server and run the experiments on the PennTreeBank
+
*modify the code to MN grammar and run the experiments
−
*read the code of rnng and MemNN
+
 
|-
 
|-
 
|Jiyuan Zhang ||
 
|Jiyuan Zhang ||
−
*completed the illustration of my part of book [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/4/46/Deep_learning-zhang_jiyuan.pdf here]]
+
*ran two versions of the code that qixin gave me,the last version of the result is good
−
*read two papers about generation task [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c7/Automatic_poetry_composition_through_recurrent_neural_networks_with_iterative_polishing_schema.pdf here]] [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/ed/Chinese_couplet_generation_with_neural_network_structures.pdf here]]
+
*perfected my poem's code
−
*checked  qixi’ newly code
+
*Results for all versions of the code[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/7/72/Theme.pdf here]]
 
||
 
||
−
*generate the same level poem compared to qx’s
+
*perfect my code  according to up-to-date version of qixin's code
 
|-
 
|-
 
|Aodong Li ||  
 
|Aodong Li ||  
第24行： 第24行：
 
|-
 
|-
 
|Andi Zhang ||
 
|Andi Zhang ||
−
*read several papers about memory network & IE
+
*read the sorce code of MemN2N
−
*tried to set the env for source code
+
*installed torch
−
*ran several times of source code on my laptop, didn't get as good results as in the paper but is close
+
 
||
 
||
−
*work on rnng
+
*try to fit the params of rnng into memn2n
−
*share a paper about IE
+
 
|-
 
|-
 
|Shiyao Li ||
 
|Shiyao Li ||
−
*prepare for the paper sharing
+
 
−
*review the chapter 8 of the book written by Maoning Wang
+
−
*learn how to use cvs and how to write books using Latex
+
 
||
 
||
−
*complete the chapter 8-nonparametric model
+
 
−
*prepare to write Genetic Algorithm
+
 
|-
 
|-
 
|Shiyue Zhang ||  
 
|Shiyue Zhang ||  
−
*Read the paper RNNG
+
*ran rnng code successfully: the result of discriminative model is a bit better than original paper; the generative model has not fully trained, so the performance is worse.
−
*Help with paper checks
+
−
*Try to run the code of RNNG
+
 
||
 
||
 +
*get generative model f1 score
 +
*get the states of each timestep
 
|-
 
|-
 
|}
 
|}

2016年9月26日 (一) 06:18的最后版本

Date People Last Week This Week
2016/09/26 Yang Feng
  • prepared the phrasal check of Huilan
  • prepared and discussed the main idea of next work
  • learned Lua and Torch and read the code of MemNN
  • read the code of rnng
  • modify the code to MN grammar and run the experiments
Jiyuan Zhang
  • ran two versions of the code that qixin gave me,the last version of the result is good
  • perfected my poem's code
  • Results for all versions of the code[here]
  • perfect my code according to up-to-date version of qixin's code
Aodong Li
Andi Zhang
  • read the sorce code of MemN2N
  • installed torch
  • try to fit the params of rnng into memn2n
Shiyao Li
Shiyue Zhang
  • ran rnng code successfully: the result of discriminative model is a bit better than original paper; the generative model has not fully trained, so the performance is worse.
  • get generative model f1 score
  • get the states of each timestep
取自“http://index.cslt.org/mediawiki/index.php?title=NLP_Status_Report_2016-09-26&oldid=22827”