“NLP Status Report 2017-8-7”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"|2017/7/3 |Jiyuan Zhang || *made the poster for ACL [http://cslt.riit.tsinghua.edu.cn/...”为内容创建页面)
 
第4行: 第4行:
 
| rowspan="6"|2017/7/3
 
| rowspan="6"|2017/7/3
 
|Jiyuan Zhang ||
 
|Jiyuan Zhang ||
*made the poster for ACL [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/95/Acl2017-poster.pdf]
+
*generated streame according to a couplet
*attempted to fix repeated word, but failed
+
*almost completed the task of filling in the blanks of a couplet
*done some work of n-gram model of the couplet
+
 
||  
 
||  
*generate streame according to a couplet
+
*continue to perfect the couplet model
*complete the task of filling in the blanks of a couplet
+
 
+
 
|-
 
|-
 
|Aodong LI ||
 
|Aodong LI ||

2017年8月7日 (一) 04:29的版本

Date People Last Week This Week
2017/7/3 Jiyuan Zhang
  • generated streame according to a couplet
  • almost completed the task of filling in the blanks of a couplet
  • continue to perfect the couplet model
Aodong LI
  • Got 55,000+ Englsih poems and 260,000+ lines after preprocessing
  • Added phase separators as the style indicator, and every line has at least one separator
  • Training loss didn't decrease very much, only from 440 to 50
  • The translation quality deteriorated when added language model
  • Try to use a larger language model to decrease the training loss
  • Try to use character-based MT in English-Chinese translation
Shiyue Zhang
Shipan Ren
  • looked for the performance(the bleu value) of other models
 on the WMT2014 dataset from the published papers,but not found.
  • installed and built Moses on the server
  • train statistical machine translation model and test it
 toolkit: Moses
 data sets:WMT2014 en-de、en-fr data sets
  • collate experimental results.compare our baseline model with Moses
Jiayu Guo
  • process document.Until now, Shiji has been split up to 2,4000 pairs of sentence.
  • Zizhitongjian has been split up to 1,6000 pairs.
  • adjust jieba source code, in order to make jieba more accurate for ancient language wordpiece
  • read model source code