NLP Status Report 2017-8-7 - 版本历史

2017年8月21日 (一) 00:48 Renshipan

2017-08-21T00:48:52Z

2017年8月7日 (一) 05:45 Guojiayu

2017-08-07T05:45:22Z

2017年8月7日 (一) 05:44 Guojiayu

2017-08-07T05:44:57Z

2017年8月7日 (一) 05:08 Renshipan

2017-08-07T05:08:16Z

2017年8月7日 (一) 04:29 Zhangjy

2017-08-07T04:29:08Z

Zhangjy：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

2017-08-07T04:27:54Z

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

新页面

{| 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/mediawiki/images/9/95/Acl2017-poster.pdf]
*attempted to fix repeated word, but failed
*done some work of n-gram model of the couplet
||
*generate streame according to a couplet
*complete the task of filling in the blanks of a couplet

|-
|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
|-
|}

@@ 第43行： / 第43行： @@
 |-
 ||
-||-
+||
 *run Shiji-based model
 *combine Shiji and Zizhitongjian,then run the model

@@ 第2行： / 第2行： @@
 !Date !! People !! Last Week !! This Week
 |-
-| rowspan="6"|2017/7/3
+| rowspan="6"|2017/8/7
 |Jiyuan Zhang ||
 *generated streame according to a couplet

@@ 第42行： / 第42行： @@
 *read model source code
 |-
-|}
+||

@@ 第10行： / 第10行： @@
 |-
 |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 ||
@@ 第24行： / 第20行： @@
 |-
 |Shipan Ren ||
 * 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
 |-

@@ 第4行： / 第4行： @@
 | rowspan="6"|2017/7/3
 |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 ||