NLP Status Report 2017-1-3 - 版本历史

2017年1月3日 (二) 07:02 Fengyang

2017-01-03T07:02:26Z

2017-01-03T07:01:21Z

2017-01-03T06:18:29Z

2017-01-03T06:12:16Z

2017-01-03T06:10:13Z

2017-01-03T06:09:45Z

2017-01-03T06:08:59Z

2017-01-03T06:04:35Z

2017-01-03T06:03:45Z

2017-01-03T05:50:23Z

@@ 第9行： / 第9行： @@
 *wrote the code for bleu evaluation;
 *managed to fix the code of nmt+mn;
-*ran experiments;
+*ran experiments [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Nmt_mn_report.pdf report]]
 ||
 *[[nmt+mn:]] do further experiments.

@@ 第5行： / 第5行： @@
 |Yang Feng ||
 *[[nmt+mn:]] tried to improve the nmt baseline;
 *read the code of Andy's;
 *wrote the code for bleu evaluation;

@@ 第7行： / 第7行： @@
 *read the code of Andy's;
 *wrote the code for bleu evaluation;
-*finished the code of nmt+mn;
+*managed to fix the code of nmt+mn;
 *ran experiments;
 ||

@@ 第39行： / 第39行： @@
 |Guli ||
 * run nmt with monolingual data
-* learn about tensorflow
+* bleu computation
-* read papers
+* learn about tensorflow
 ||
 * improve my paper

@@ 第2行： / 第2行： @@
 !Date !! People !! Last Week !! This Week
 |-
-| rowspan="6"|2016/12/26
+| rowspan="6"|2017/1/3
 |Yang Feng ||
 *[[nmt+mn:]] tried to improve the nmt baseline;

@@ 第38行： / 第38行： @@
 |-
 |Guli ||
-* finished the first draft of the survey
+* run nmt with monolingual data
-* voice tagging
+* learn about tensorflow
 ||
-* morpheme-based nmt
+* improve my paper
-* improve nmt with monolingual data
+* analyze experiment results
 |-
 |Peilun Xiao ||

@@ 第13行： / 第13行： @@
 |-
 |Jiyuan Zhang ||
-*integrated tone_model to attention_model for insteading manul rule,but the effect wasn't good
+*improved speed of prediction process
-*replacing　all_pz rule with half_pz
+*ran expriments:<br/>
-*token a classical Chinese as input,generated poem [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/33/Story_input.pdf]
+two sytles expriments of top1_memory_model<br/>
 ||
 *improve poem model

@@ 第28行： / 第28行： @@
 |Shiyue Zhang ||
 * tried to improve rnng+mm model, but still failed  [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/9f/RNNG%2Bmm_experiment_report.pdf report]]
-* stop rnng work to help Teacher Feng with NMT
+* stopped rnng work to help Teacher Feng with NMT
 * ran theano NMT code successfully, and found a problem of test
 ||

@@ 第27行： / 第27行： @@
 |-
 |Shiyue Zhang ||
-* tried to add true action info when training gate, which got better results than no true actions, but still not very good.
+* tried to improve rnng+mm model, but still failed  [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/9f/RNNG%2Bmm_experiment_report.pdf report]]
-* tried different scale vectors, and found setting >=-5000 is good
+* stop rnng work to help Teacher Feng with NMT
-* tried to change cos to only inner product, and inner product is better than cos.
+* ran theano NMT code successfully, and found a problem of test
-* [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/9f/RNNG%2Bmm_experiment_report.pdf report]]
-* read 3 papers [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/92/DEEP_BIAFFINE_ATTENTION_FOR_NEURAL_DEPENDENCY_PARSING.pdf]] [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/a/aa/Simple_and_Accurate_Dependency_Parsing_Using_Bidirectional_LSTM_Feature_Representations.pdf]] [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/fb/Bi-directional_Attention_with_Agreement_for_Dependency_Parsing.pdf]]
-* trying the joint training, which got a problem of optimization.
 ||
-* try the joint training
+* run and test the theano NMT model
-* read more papers and write a summary
+* try to modify tensorflow NMT model, run and test
 |-
 |Guli ||

@@ 第20行： / 第20行： @@
 |-
 |Andi Zhang ||
-*coded to output encoder outputs and correspoding source & target sentences(ids in dictionaries)
+*handed in previous codes to Mrs.Feng
-*coded a script for bleu scoring, which tests the five checkpoints auto created by training process and save the one with best performance
+*help Jiyuan gather poems about tianyuan
 ||
+*help Jiyuan with his work
 |-
 |Shiyue Zhang ||