“NLP Status Report 2017-8-7”版本间的差异

2017年8月7日 (一) 05:08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
	Shiyue Zhang
	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 en-de dataset Moses:15.4 Baseline:14.87 en-fr datasets under training	read memory-augment NMT code think about the next step work
	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 ||
-* 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
+  en-de dataset
+  Moses:15.4
+  Baseline:14.87
+  en-fr datasets
+  under training
+||
+* read memory-augment NMT code
+* think about the next step work
 |-