NLP Status Report 2016-11-14 - 版本历史

2016年11月15日 (二) 00:57 Zhangjy

2016-11-15T00:57:39Z

2016年11月14日 (一) 05:22 Zhangsy

2016-11-14T05:22:22Z

2016年11月14日 (一) 05:22 Zhangsy

2016-11-14T05:22:06Z

2016年11月14日 (一) 05:21 Zhangsy

2016-11-14T05:21:46Z

2016年11月14日 (一) 05:17 Zhangjy

2016-11-14T05:17:31Z

2016年11月14日 (一) 04:43 Zhangandy

2016-11-14T04:43:30Z

2016年11月14日 (一) 04:40 Fengyang

2016-11-14T04:40:03Z

2016年11月14日 (一) 04:39 Fengyang

2016-11-14T04:39:29Z

Fengyang：以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="4"|2016/10/31 |Yang Feng || * ran rnng+MN with offline lstm states, but failed, as the a...”为内容创建页面

2016-11-14T04:26:39Z

以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="4"|2016/10/31 |Yang Feng || * ran rnng+MN with offline lstm states, but failed, as the a...”为内容创建页面

新页面

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="4"|2016/10/31
|Yang Feng ||
* ran rnng+MN with offline lstm states, but failed, as the actions in oracle and lstm states conflicted.
* wrote the code to generate lstm states online and ran some experiments. [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f8/Progress_of_RNNG_with_memory_network.pdf report]]
* transferred the code to Shiyue.
||
* optimize rnng+MN;
* do the work of sequence-to-sequence generation;
* Huilan work.
|-
|Jiyuan Zhang ||

||

|-
|Andi Zhang ||

||

|-
|Shiyue Zhang ||

||

|-
|}

@@ 第21行： / 第21行： @@
 ||
 *continue to modify memory model
 |-
 |Andi Zhang ||

@@ 第35行： / 第35行： @@
 * try rnng on GPU
 * read the code of Feng
-* modify model
+* modify model [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/2f/RNNG%2Bmm%E5%AE%9E%E9%AA%8C%E6%8A%A5%E5%91%8A.pdf report]
 [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/2f/RNNG%2Bmm%E5%AE%9E%E9%AA%8C%E6%8A%A5%E5%91%8A.pdf report]
 ||
 * try MKL

@@ 第36行： / 第36行： @@
 * read the code of Feng
 * modify model
-[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/2f/RNNG%2Bmm%E5%AE%9E%E9%AA%8C%E6%8A%A5%E5%91%8A.pdf]
+[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/2f/RNNG%2Bmm%E5%AE%9E%E9%AA%8C%E6%8A%A5%E5%91%8A.pdf report]
 ||
 * try MKL

@@ 第33行： / 第33行： @@
 |-
 |Shiyue Zhang ||
+* try rnng on GPU
 ||
+* try MKL
 |-
 |}

@@ 第22行： / 第22行： @@
 |-
 |Andi Zhang ||
+*ran NMT (cs-en) on gpu, but bleu is low, could be resulting from a small corpus
 ||
+*run NMT (fr-en) to get a bleu as that in the paper
 |-
 |Shiyue Zhang ||

@@ 第17行： / 第17行： @@
 |-
 |Jiyuan Zhang ||
+*checked previous code about encoder-memory
 ||
+*continue to modify memory model
 |-
 |Andi Zhang ||

@@ 第7行： / 第7行： @@
 * ran experiments for rnng+mn [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f8/Progress_of_RNNG_with_memory_network.pdf report]]
 * read the code of sequence-to-sequence with tensorflow
-* recruit interns
+* recruited interns
 * Huilan work summary
 ||

@@ 第4行： / 第4行： @@
 | rowspan="4"|2016/10/31
 |Yang Feng ||
-* ran rnng+MN with offline lstm states, but failed, as the actions in oracle and lstm states conflicted.
+* added new features to rnng+mn, including automatically detecting wrong sentences, swapping  memories more frequently and filtering memory units to speed up.
-* wrote the code to generate lstm states online and ran some experiments. [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f8/Progress_of_RNNG_with_memory_network.pdf report]]
+* ran experiments for rnng+mn [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f8/Progress_of_RNNG_with_memory_network.pdf report]]
-* transferred the code to Shiyue.
+* read the code of sequence-to-sequence with tensorflow
 ||
 * optimize rnng+MN;
-* do the work of sequence-to-sequence generation;
+* discuss the code with Jiyuan;
 *  Huilan work.
 |-