|
|
| 第4行： |
第4行： |
| | | rowspan="6"|2016/12/26 | | | rowspan="6"|2016/12/26 |
| | |Yang Feng || | | |Yang Feng || |
| − | *[[s2smn:]] read six papers to fix the details of our model; | + | *[[s2smn:]] tried to improve the nmt baseline; |
| − | *wrote the proposal of lexical memory and discussed the details with Teach Wang; | + | *read the code of Andy's; |
| − | *finished coding of only adding attention to the decoder and under debugging; | + | *write the code for bleu test; |
| − | *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]] ; | + | *finished the code of nmt+mn; |
| − | *prepare the dictionary for the memory loading; | + | *ran experiments; |
| − | *[[Huilan:]] documentation
| + | |
| | || | | || |
| − | *[[s2smn:]] run the ecperiments. | + | *[[s2smn:]] do further ecperiments. |
| − | *[[rnng+mn:]] try to find the problem.
| + | |
| | |- | | |- |
| | |Jiyuan Zhang || | | |Jiyuan Zhang || |
| Date |
People |
Last Week |
This Week
|
| 2016/12/26
|
Yang Feng |
- s2smn: tried to improve the nmt baseline;
- read the code of Andy's;
- write the code for bleu test;
- finished the code of nmt+mn;
- ran experiments;
|
- s2smn: do further ecperiments.
|
| Jiyuan Zhang |
- integrated tone_model to attention_model for insteading manul rule,but the effect wasn't good
- replacing all_pz rule with half_pz
- token a classical Chinese as input,generated poem [1]
|
|
| Andi Zhang |
- coded to output encoder outputs and correspoding source & target sentences(ids in dictionaries)
- coded a script for bleu scoring, which tests the five checkpoints auto created by training process and save the one with best performance
|
|
| 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 different scale vectors, and found setting >=-5000 is good
- tried to change cos to only inner product, and inner product is better than cos.
- [report]
- read 3 papers [[2]] [[3]] [[4]]
- trying the joint training, which got a problem of optimization.
|
- try the joint training
- read more papers and write a summary
|
| Guli |
- finished the first draft of the survey
- voice tagging
|
- morpheme-based nmt
- improve nmt with monolingual data
|
| 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
|
