NLP Status Report 2017-8-21 - 版本历史

2017年8月28日 (一) 07:44 Renshipan

2017-08-28T07:44:30Z

2017-08-21T06:47:46Z

2017-08-21T06:41:54Z

2017-08-21T06:37:32Z

2017-08-21T05:16:41Z

2017-08-21T05:13:42Z

2017-08-21T05:09:46Z

2017-08-21T05:04:48Z

2017-08-21T05:03:10Z

2017-08-21T04:25:43Z

@@ 第19行： / 第19行： @@
 |-
 |Shipan Ren ||
-* organized all the experimental results(our baseline system,Moses,THUMT)
+* organized all the experimental results(our baseline system,Moses,THUMT) [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/8/89/Nmt_baseline.xlsx]
 * trained and tested translation models（Toolkit:THUMT ）
 * compared with our system

@@ 第47行： / 第47行： @@
 *The main factors now is the data(pairs of sentence/the quality——the modern language text includes context information).
 ||
-*plan to read source code of seq2seq model;
+*plan to read source code of seq2seq model and learn tensorflow;
 *plan to read a paper named Automatic Long Sentence Segmentation for NMT
 |-
 |}

@@ 第45行： / 第45行： @@
 *3.data used Shiji and Zizhitongjian(43,0000 pairs), we can get BLEU about 9.
 *4.data used Shiji and Zizhitongjian(43,0000 pairs), and split the ancient language text one character by one, we can get BLEU 11.11 at most.
-*The main factors now is the data(including pairs of sentence、the quality——cause the modern language text include context information.
+*The main factors now is the data(pairs of sentence/the quality——the modern language text includes context information).
 ||
 *plan to read source code of seq2seq model;

@@ 第41行： / 第41行： @@
 *target:现天子继承汉朝千年一统的大业，在泰山举行封禅典礼而我不能随行，这是命啊，是命啊！
 *trans: 现在天子可以继承帝位的成就爵位，爵位至泰山，而我却未能执行先帝的命运。
 *1.data used Zizhitongjian only(6,000 pairs), we can get BLEU 6 at most.
 *2.data used Zizhitongjian only(12,000 pairs), we can get BLEU 7 at most.
@@ 第49行： / 第46行： @@
 *4.data used Shiji and Zizhitongjian(43,0000 pairs), and split the ancient language text one character by one, we can get BLEU 11.11 at most.
 *The main factors now is the data(including pairs of sentence、the quality——cause the modern language text include context information.
 |-
 |}

@@ 第20行： / 第20行： @@
 |Shipan Ren ||
 * organized all the experimental results(our baseline system,Moses,THUMT)
-* train translation models by using THUMT
+* trained and tested translation models（Toolkit:THUMT ）
-* test the bleu of these models
+* compared with our system
-* compare with our system
 ||
 * prepare to release the baseline system（tensorflow1.0 version）

@@ 第4行： / 第4行： @@
 | rowspan="6"|2017/8/14
 |Jiyuan Zhang ||
-*done work about code refactoring for poem system
+*done some work about code refactoring for poem system
 ||
 *plan to complete code refactoring for poem system

@@ 第1行： / 第1行： @@
 {| class="wikitable"
-!Date!!People !! Last Week !! This Week
+!Date !! People !! Last Week !! This Week
 |-
-| rowspan="7"|2017.8.21
+| rowspan="6"|2017/8/14
 |-
-|GuoJiayu
+|Shiyue Zhang ||
-||
 * process data and run model;
 * test results.
@@ 第30行： / 第51行： @@
 *The main factors now is the data(including pairs of sentence、the quality——cause the modern language text include context information.
 |-
 |}

@@ 第8行： / 第8行： @@
 ||
 * process data and run model;
 ||
 * read source code of seq2seq model;
 |-
 |}