NLP Status Report 2017-7-10 - 版本历史

2017年8月21日 (一) 00:31 Renshipan

2017-08-21T00:31:04Z

2017年7月10日 (一) 06:18 Renshipan

2017-07-10T06:18:13Z

2017年7月10日 (一) 06:16 Renshipan

2017-07-10T06:16:31Z

2017年7月10日 (一) 05:58 Renshipan

2017-07-10T05:58:45Z

2017年7月10日 (一) 04:53 Intern

2017-07-10T04:53:54Z

2017年7月10日 (一) 04:53 Intern

2017-07-10T04:53:39Z

2017年7月10日 (一) 04:48 Zhangjy

2017-07-10T04:48:29Z

Zhangjy：以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/7/3 |Jiyuan Zhang || || |- |Aodong LI || * Tried seq2seq with or without attent...”为内容创建页面

2017-07-10T04:41:28Z

以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/7/3 |Jiyuan Zhang || || |- |Aodong LI || * Tried seq2seq with or without attent...”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 ||
||
|-
|Aodong LI ||
* Tried seq2seq with or without attention model to do style transfer (cross domain) task but this didn't work due to overfitting
seq2seq with attention model: Chinese-to-English
vanilla seq2seq model: English-to-English (Unsupervised)
* Read two style controlled papers in generative model field
* Trained seq2seq with style code model
||
* Understand the model and mechanism mentioned in the two related papers
* Figure out new ways to do style transfer task
|-
|Shiyue Zhang ||

||

|-
|Shipan Ren ||
* read and run ViVi_NMT code
* read the API of tensorflow
* debugged ViVi_NMT and upgraded code version to tensorflow1.0
* found the new version saves more time，has lower complexity and better bleu than before
||
* test two versions of the code on small data sets (Chinese-English) and large data sets (Chinese-English) respectively
* test two versions of the code on WMT 2014 English-to-German parallel dataset and WMT 2014 English-French dataset respectively
* record experimental results
* read paper and try to make the bleu become a little better
|-

|}

@@ 第23行： / 第23行： @@
 * run two versions of the code on small data sets (Chinese-English)  and tested these checkpoint
       found version 1.0 save time about 0.03s  per step,
-     and these two version  has  similar complexity and bleu values
+           and these two version  has  similar complexity and bleu values
       found that the bleu is still good when the model is over fitting .
-     (reason: the test set and the train set of small data set are similar in content and style)
+           (reason: the test set and the train set of small data set are similar in content and style)
-* run two versions of the code on big data sets (Chinese-English) . OOM（Out Of Memory）
+* run two versions of the code on big data sets (Chinese-English) .
-     error occurred when version 0.1 was trained using large data set，but version 1.0 worked
+     OOM（Out Of Memory） error occurred when version 0.1 was trained using large data set，but version 1.0 worked
-     reason: improper distribution of resources by the tensorflow0.1 frame leads to exhaustion of memory resources
+          reason: improper distribution of resources by the tensorflow0.1 frame leads to exhaustion of memory resources
       I had tried 4 times （just enter the same command）, and version 0.1 worked
-     found version 1.0 save time about 0.06s  per step, and these two version  has  similar complexity and bleu values
+          found version 1.0 save time about 0.06s  per step, and these two version  has  similar complexity and bleu values
 * downloaded the wmt2014 data set ,used the English-French data set to run the code and
      found the translation is not good (reason:improper word segmentation)

@@ 第22行： / 第22行： @@
 |Shipan Ren ||
 * run two versions of the code on small data sets (Chinese-English)  and tested these checkpoint
-      found version 1.0 save time about 0.03s  per step, and these two version  has  similar complexity and bleu values
+      found version 1.0 save time about 0.03s  per step,
-      found that the bleu is still good when the model is over fitting . (reason: the test set and the train set of small data set are similar in content and style)
+     and these two version  has  similar complexity and bleu values
-* run two versions of the code on big data sets (Chinese-English) . OOM（Out Of Memory） error occurred when version 0.1 was trained using large data set，but version 1.0 worked
+      found that the bleu is still good when the model is over fitting .
       reason: improper distribution of resources by the tensorflow0.1 frame leads to exhaustion of memory resources
       I had tried 4 times （just enter the same command）, and version 0.1 worked
       found version 1.0 save time about 0.06s  per step, and these two version  has  similar complexity and bleu values
-* downloaded the wmt2014 data set ,used the English-French data set to run the code and found the translation is not good (reason:improper word segmentation)
+* downloaded the wmt2014 data set ,used the English-French data set to run the code and
 ||
 * do word segmentation on wmt2014  data set

@@ 第10行： / 第10行： @@
 |Aodong LI ||
 * Tried a seq2seq with style code model but it didn't work.
-* Coding attention-based seq2seq NMT in shallow fusion with a language model.
+* Coded attention-based seq2seq NMT in shallow fusion with a language model.
 ||
 * Complete coding and have a try.

@@ 第2行： / 第2行： @@
 !Date !! People !! Last Week !! This Week
 |-
-| rowspan="6"|2017/7/3
+| rowspan="6"|2017/7/10
 |Jiyuan Zhang ||
 *reproduced the couplet model using moses

@@ 第21行： / 第21行： @@
 |-
 |Shipan Ren ||
-* read and run ViVi_NMT code
+* run two versions of the code on small data sets (Chinese-English)  and tested these checkpoint
-* read the API of tensorflow
+     found version 1.0 save time about 0.03s  per step, and these two version  has  similar complexity and bleu values
-* debugged ViVi_NMT and  upgraded code version to tensorflow1.0
+     found that the bleu is still good when the model is over fitting . (reason: the test set and the train set of small data set are similar in content and style)
-* found the new version saves more time，has lower complexity and better bleu than before
+* run two versions of the code on big data sets (Chinese-English) . OOM（Out Of Memory） error occurred when version 0.1 was trained using large data set，but version 1.0 worked
 ||
-* test two versions of the code on small data sets (Chinese-English) and large data sets (Chinese-English) respectively
+* do word segmentation on wmt2014  data set
-* test two versions of the code on WMT 2014 English-to-German parallel dataset and WMT 2014 English-French dataset respectively
+* run two versions of the code on wmt2014  data set
-* record experimental results
+* record the result and do analysis
-* read paper and try to make the bleu become a little better
+* learn and train moses(use big data sets (Chinese-English))
 |-
 |}

@@ 第9行： / 第9行： @@
 |-
 |Aodong LI ||
-* Tried seq2seq with or without attention model to do style transfer (cross domain) task but this didn't work due to overfitting
+* Tried a seq2seq with style code model but it didn't work.
-  seq2seq with attention model: Chinese-to-English
+* Coding attention-based seq2seq NMT in shallow fusion with a language model.
-  vanilla seq2seq model: English-to-English (Unsupervised)
-* Read two style controlled papers in generative model field
-* Trained seq2seq with style code model
 ||
-* Understand the model and mechanism mentioned in the two related papers
+* Complete coding and have a try.
-* Figure out new ways to do style transfer task
+* Find more monolingual corpus and upgrade the model.
 |-
 |Shiyue Zhang ||