NLP Status Report 2016-12-19 - 版本历史

2016年12月26日 (一) 00:58 Zhangandy

2016-12-26T00:58:07Z

2016-12-20T05:21:11Z

2016-12-20T05:20:30Z

2016-12-19T06:25:46Z

2016-12-19T06:24:41Z

2016-12-19T05:36:58Z

2016-12-19T05:33:45Z

2016-12-19T05:27:20Z

2016-12-19T05:23:12Z

2016-12-19T05:21:57Z

@@ 第20行： / 第20行： @@
 |-
 |Andi Zhang ||
-*tried to modify the wrong softmax, but abandoned at last
+*coded to output encoder outputs and correspoding source & target sentences(ids in dictionaries)
-*added bleu scoring part
+*coded a script for bleu scoring, which tests the five checkpoints auto created by training process and save the one with best performance
 ||
 *extract encoder outputs

@@ 第44行： / 第44行： @@
 |-
 |Peilun Xiao ||
-*Use LDA to generate 10-500 dimension document vector in the rest datasets
+*use LDA to generate 10-500 dimension document vector in the rest datasets
-*Write a python code about a new algorithm about tf-idf
+*write a python code about a new algorithm about tf-idf
 ||
-*Debug the code
+*debug the code
 |}

@@ 第44行： / 第44行： @@
 |-
 |Peilun Xiao ||
-*Read a paper about document classification wiht GMM distributions of word vecotrs and try to code it in python
+*Use LDA to generate 10-500 dimension document vector in the rest datasets
-*Use LDA to reduce the dimension of the text in r52、r8 and contrast the performance of classification
+*Write a python code about a new algorithm about tf-idf
 ||
-*Use LDA to reduce the dimension of the text in 20news and webkb
+*Debug the code
 |}

@@ 第15行： / 第15行： @@
 |Jiyuan Zhang ||
 *coded tone_model,but had some trouble
-*run global_attention_model that decodes four sentences, [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/d/d5/Four_local_atten.pdf four][ five]generated by local_attention model
+*run global_attention_model that decodes four sentences, [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/d/d5/Four_local_atten.pdf four][http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/05/Five_local_attention.pdf five]generated by local_attention model
 ||
 *improve poem model

@@ 第15行： / 第15行： @@
 |Jiyuan Zhang ||
 *coded tone_model,but had some trouble
-*run global_attention_model that decodes four sentences, generated by local_attention model
+*run global_attention_model that decodes four sentences, [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/d/d5/Four_local_atten.pdf four][ five]generated by local_attention model
 ||
 *improve poem model

@@ 第14行： / 第14行： @@
 |-
 |Jiyuan Zhang ||
-*attempted to use memory model to improve the atten model of bad effect
+*coded tone_model,but had some trouble
-*With the vernacular as the input，generated poem by local atten model[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/2f/Local_atten_resluts.pdf]
+*run four_attention_model, generated by local_attention model
-*Modified working mechanism of memory model(top1 to average)
-*help andi
 ||
 *improve poem model

@@ 第22行： / 第22行： @@
 |-
 |Andi Zhang ||
-*prepared a paraphrase data set that is enumerated from a previous one (ignoring words like "啊呀哈")
+*tried to modify the wrong softmax, but abandoned at last
-*worked on coding bidirectional model under tensorflow, met with NAN problem
+*added bleu scoring part
 ||
-*ignore NAN problem for now, run it on the same data set used in Theano
+*extract encoder outputs
 |-
 |Shiyue Zhang ||

@@ 第2行： / 第2行： @@
 !Date !! People !! Last Week !! This Week
 |-
-| rowspan="6"|2016/12/12
+| rowspan="6"|2016/12/19
 |Yang Feng ||
 *[[s2smn:]] wrote the manual of s2s with tensorflow [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/51/Nmt-tensorflow-mannua-yfeng.pdf nmt-manual]]
@@ 第39行： / 第39行： @@
 |-
 |Guli ||
-*install and run moses
+*read papers about Transfer learning and solving OOV
-*prepare thesis report
+*conducted comparative test
 ||
-*read papers about Transfer learning and solving OOV
+* complete the first draft of the survey
 |-
 |Peilun Xiao ||

@@ 第32行： / 第32行： @@
 * tried to only train gate, but the best is taking all instance as "right"
 * trying a model similar to attention
-* [[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/9/9f/RNNG%2Bmm_experiment_report.pdf report]]
 ||
-* change one-hot vector to (0, -10000.0, -10000.0...)
+* try to add true action info when training gate
-* try 1-dim gate
+* try different scale vectors
-* try max cos
+* try to change cos to only inner product
 |-
 |Guli ||