|
|
| （5位用户的13个中间修订版本未显示） |
| 第2行： |
第2行： |
| | !Date !! People !! Last Week !! This Week | | !Date !! People !! Last Week !! This Week |
| | |- | | |- |
| − | | rowspan="6"|2016/12/26 | + | | rowspan="6"|2017/1/3 |
| | |Yang Feng || | | |Yang Feng || |
| − | *[[s2smn:]] read six papers to fix the details of our model; | + | *[[nmt+mn:]] tried to improve the nmt baseline; |
| − | *wrote the proposal of lexical memory and discussed the details with Teach Wang; | + | *met with problems for baseline, rulling out the factor of output order and file format and got the reason of learning rate. |
| − | *finished coding of only adding attention to the decoder and under debugging; | + | *read the code of Andy's; |
| − | *refine Moses manual [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/92/Moses%E6%93%8D%E4%BD%9C%E6%89%8B%E5%86%8C--%E5%86%AF%E6%B4%8B.pdf manual]] ; | + | *wrote the code for bleu evaluation; |
| − | *prepare the dictionary for the memory loading;
| + | *managed to fix the code of nmt+mn; |
| − | *[[Huilan:]] documentation
| + | *ran experiments [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Nmt_mn_report.pdf report]] |
| | || | | || |
| − | *[[s2smn:]] run the ecperiments. | + | *[[nmt+mn:]] do further experiments. |
| − | *[[rnng+mn:]] try to find the problem.
| + | |
| | |- | | |- |
| | |Jiyuan Zhang || | | |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/> |
| | + | overfitting expriments of top1_memory_model<br/> |
| | + | two styles expriments of average_memory_model<br/> |
| | + | overfitting expirments of average_memory_model |
| | || | | || |
| | *improve poem model | | *improve poem model |
| | |- | | |- |
| | |Andi Zhang || | | |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 |
| | + | *gather more poems |
| | |- | | |- |
| | |Shiyue Zhang || | | |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
| + | * stopped 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 || | | |Guli || |
| − | * finished the first draft of the survey | + | * run nmt with monolingual data |
| − | * voice tagging | + | * bleu computation |
| | + | * learn about tensorflow |
| | || | | || |
| − | * morpheme-based nmt | + | * improve my paper |
| − | * improve nmt with monolingual data | + | * analyze experiment results |
| | |- | | |- |
| | |Peilun Xiao || | | |Peilun Xiao || |
| Date |
People |
Last Week |
This Week
|
| 2017/1/3
|
Yang Feng |
- nmt+mn: tried to improve the nmt baseline;
- met with problems for baseline, rulling out the factor of output order and file format and got the reason of learning rate.
- read the code of Andy's;
- wrote the code for bleu evaluation;
- managed to fix the code of nmt+mn;
- ran experiments [report]
|
|
| Jiyuan Zhang |
- improved speed of prediction process
- ran expriments:
two sytles expriments of top1_memory_model
overfitting expriments of top1_memory_model
two styles expriments of average_memory_model
overfitting expirments of average_memory_model
|
|
| Andi Zhang |
- handed in previous codes to Mrs.Feng
- help Jiyuan gather poems about tianyuan
|
- help Jiyuan with his work
- gather more poems
|
| Shiyue Zhang |
- tried to improve rnng+mm model, but still failed [report]
- stopped rnng work to help Teacher Feng with NMT
- ran theano NMT code successfully, and found a problem of test
|
- run and test the theano NMT model
- try to modify tensorflow NMT model, run and test
|
| Guli |
- run nmt with monolingual data
- bleu computation
- learn about tensorflow
|
- improve my paper
- analyze experiment results
|
| Peilun Xiao |
- learned tf-idf algorithm
- coded tf-idf alogrithm in python,but found it not worked well
- tried to use small dataset to test the program
|
- use sklearn tfidf to test the dataset
|
