NLP Status Report 2017-7-24 - 版本历史

2017年8月21日 (一) 00:50 Renshipan

2017-08-21T00:50:49Z

2017年7月26日 (三) 05:01 Intern

2017-07-26T05:01:23Z

2017年7月26日 (三) 03:59 Renshipan

2017-07-26T03:59:12Z

2017年7月26日 (三) 03:40 Renshipan

2017-07-26T03:40:03Z

Zhangjy：以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/7/3 |Jiyuan Zhang || * || make the poster for ACL complete neural model for t...”为内容创建页面

2017-07-26T02:41:06Z

以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/7/3 |Jiyuan Zhang || * || *make the poster for ACL *complete neural model for t...”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 ||
*
||
*make the poster for ACL
*complete neural model for the couplet
|-
|Aodong LI ||
*

||
*
|-
|Shiyue Zhang ||

||

|-
|Shipan Ren ||
* found ways to tokenize the WMT2014 data
rewrote prepare_data.py form moses-smt
used the tokenizer of moses-smt

*train two versions of the code on WMT2014 en-de and en-fr datasets
tested these checkpoints of en-de dataset

||
* tested these checkpoints of en-fr dataset
* record the result and do analysis
* read papers about memory augmented NMT
|-

|}

@@ 第10行： / 第10行： @@
 |-
 |Aodong LI ||
+* Completed the shallow fusion of news-domain translation with dialog-domain style.
 ||
+* Find the dataset with obvious style indicators.
 |-
 |Shiyue Zhang ||

@@ 第21行： / 第21行： @@
 |-
 |Shipan Ren ||
-*train two versions of the code on WMT2014 en-de and en-fr datasets
+* trained two models of the baseline using WMT2014 en-fr datasets
    under training
    new version saved more time
-*read paper（memory-augmented-nmt and Memory augmented Chinese-Uyghur Neural Machine Translation）
+* read some papers（memory-augmented-nmt and Memory augmented Chinese-Uyghur Neural Machine Translation）
-−
 ||
 * read memory-augmented-nmt code