cslt Wiki - 用户贡献 [zh-cn]

Asr-nsfc-weekly-2017-02-13

2017-02-14T04:37:33Z

Guli：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="5"|2017.02.13
|-
|清华
||
* 哈萨克语语音识别系统基本完成[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=576]。
||
* 任务暂停，准备interspeech论文。
|-
|-
|新大
||
* 暂无进展
||
*
|-
|-
|民大
||
* 暂无进展
||
*
|-
|}

Asr-nsfc-weekly-2017-01-03

2017-01-04T05:08:01Z

Guli：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="5"|2017.01.03
|-
|清华
||
*哈萨克语TRP完成，生成新的test集新test集在语音模型上的ppl为192.5较为合理
||
*等新大录好新的test集以后测试
|-
|-
|新大
||
* syllable based spelling corrections are finished for 4k and 200k corpora.
* Kazak acoustic dictionary program is finished.
||
* keep work on Kazak ASR corpora problems.
|-
|-
|民大
||
*
||
*
|-
|}
------------------------------------------------------------------------------------------------------------------------
{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="5"|2016.12.26
|-
|清华
||
*新AM训练完毕，使用网上抓取的数据做了新的LM但是所抓取内容是否有实际意义，有没有抓错无法验证。
||
* 写哈萨克语的TRP
|-
|-
|新大
||
* 通过两次会议，确定了哈语的音节规则，并根据音节规则检查拼写。发现并更正100多个拼写错误。
||
* 20万句子的拼写纠错及发音辞典的建立。
|-
|-
|民大
||
* 完成藏语拉萨话口语翻译800句。
||
* 分别准备藏语及蒙语书面语发音文本9万句和6万句。
|-
|}

文件:Bi-Monthly report.pdf

2017-01-04T04:56:09Z

Guli：Guli上传“文件:Bi-Monthly report.pdf”的新版本

Schedule

2017-01-03T06:13:50Z

Guli：/* Daily Report */

=NLP Schedule=

==Members==

===Current Members===

* Yang Feng (冯洋)
* Jiyuan Zhang （张记袁）
* Aodong Li (李傲冬)
* Andi Zhang (张安迪)
* Shiyue Zhang (张诗悦)
* Li Gu (古丽)
* Peilun Xiao (肖培伦)

===Former Members===
* '''Chao Xing (邢超)''' : FreeNeb
* '''Rong Liu (刘荣)''' : 优酷
* '''Xiaoxi Wang (王晓曦)''' : 图灵机器人
* '''Xi Ma (马习)''' : 清华大学研究生
* '''Tianyi Luo (骆天一)''' ： phd candidate in University of California Santa Cruz
* '''Qixin Wang (王琪鑫)''' : MA candidate in University of California
* '''DongXu Zhang (张东旭)''': --
* '''Yiqiao Pan (潘一桥)''' ： MA candidate in University of Sydney
* '''Shiyao Li （李诗瑶）''' : BUPT
* '''Aiting Liu (刘艾婷)''' : BUPT

==Work Progress==
===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="3"|2016/12/1
|Andy Zhang|| 9:30||18:30 ||8 ||
*read source code
*thought about ways to store encoder output
|-
|Shiyue Zhang || 9:10 || 19:00|| 8+ ||
* draw tsne pictures
|-
|Guli ||9:10 ||9:50 ||12+ ||
*prepare data and run code
*prepare for Thesis Report
|-
| rowspan="4"|2016/12/2
|Andy Zhang|| 9:30|| 18:30|| 8||
*finish the code to output encoder output but have not tested yet
*prepared a small data set for testing
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||18:05 ||8 ||
*read code and check data
*think about how to improve bleu score
|-
|Peilun Xiao ||10:00||12:30|| 2+||
*learn basic things of work
|-
| rowspan="4"|2016/12/5
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*group meeting
*prepare the same data set as in Theano for Tensorflow
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+||
* discuss with teachers about the tsne pictures
* group meeting
|-
|Guli ||9:00 ||22:35 ||13+ ||
*install moses
*weekly report
|-
|Peilun Xiao ||9:30||18:30 ||8||
*learn how to use weka
|-
| rowspan="4"|2016/12/6
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*run fr-en (single encoder)
*prepare paraphrase data set, enumerate them, excluding 呀啊哈, etc.
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||22;30 ||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao ||9:40||18:30|| 8||
*read a paper
*use weka
|-
| rowspan="4"|2016/12/7
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*prepare paraphrase data set, enumerate them, excluding 呀啊哈, etc.
*met with some problems, used too much memory, had to restrict enumerate nums to 15000
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+||
* change mem to 28-dim states
* retry previous experiments
|-
|Guli ||9:15||22;00||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/8
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*finished preparing the data set
*start working on bidirectional model
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+||
* try more experiments, but all are not good, always converge to baseline
* draw the tsne picture of test data
* discuss with Teacher Wang
|-
|Guli ||9:15||21;15||12 ||
*run moses
*write Thesis Report
|-
|Peilun Xiao ||9:30||17:30|| 7||
*learn GibbsLda++
|-
| rowspan="4"|2016/12/9
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*finished coding, added masks for encoder inputs
*had a some breakthrough with Jiyuan's help, but still meet nan problem
|-
|Shiyue Zhang ||9:30 || 19:00 || 8+||
* return to 384-dim mem, which has 0.07 improvement than baseline
* replace cos with a one-layer neural network, which is also slightly better than baseline
* discuss with teachers, and find the problem of scale
|-
|Guli ||9:15||21;30||12 +||
*prepared Thesis Report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/12
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||10:00||19;00|| 9||
*read paper to solve oov
|-
|Peilun Xiao ||9:30||19:00||8+||
*use lda to generate document vector
|-
| rowspan="4"|2016/12/13
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*tried to modify the wrong softmax
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+ ||
* change mem scale to (0, -10000.0...)
* try previous experiments
|-
|Guli ||09:30||21;00||11+||
*read papers
|-
|Peilun Xiao ||9:50 ||19:00 || 8 ||
*use lda to generate document vector
|-
| rowspan="4"|2016/12/14
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*tried to modify the wrong softmax
*decided to abandon it for now
|-
|Shiyue Zhang || || || ||
|-
|Guli ||09:20||20;30||11+||
*read papers
*writing a survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/15
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*tried to add bleu scoring into the code, but met with out of memory problem
|-
|Shiyue Zhang || 9:30 || 19:00|| 8+||
* changed scale didn't lead to better results
* try 1-dim gate, but converge to baseline
|-
|Guli ||09:20||20;30||11+||
*read papers
*writing a survey
|-
|Peilun Xiao ||13:30||19:00||5+||
*use lda to generate document vector
|-
| rowspan="4"|2016/12/16
|Andy Zhang|| 9:20 || 18:20 || 8 ||
*finished adding bleu scoring into the code
|-
|Shiyue Zhang || 14:00 || 19:00|| 5||
* try to only train gate
* try model similar to attention
|-
|Guli ||09:30||20;30||11||
*Check the data, modify the error
*writing a survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/19
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*group meeting
*made some revises on bleu scoring
|-
|Shiyue Zhang || 9:00 || 19:00|| 9||
* review last week work
* write the report and talk with teachers
* decide what to do next and meeting
* try to train gate with true action info
|-
|Guli ||9:15||20:00||10+||
*weekly meeting
*conduct comparative test
|-
|Peilun Xiao ||9:30 ||19:00 || 8+ ||
*weekly meeting
*code on tf-idf
|-
| rowspan="4"|2016/12/20
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*dealt with some bugs on bidirectional model
*coding on getting encoder outputs
|-
|Shiyue Zhang || 9:30 ||19:00|| 8+||
* try to train gate with true actions, which gets the results better than no true action, but still not very good.
* try to change cos to inner product, which gets better performance than cos.
|-
|Guli ||9:00||21:50||12+||
*voice tagging
*write survey
|-
|Peilun Xiao ||9:50||18:30 ||8 ||
*debug the code
*prepare a small test set
|-
| rowspan="4"|2016/12/21
|Andy Zhang||9:20 || 18:30 || 8+ ||
*finishing testing on getting encoder outputs
*coded to output corresponding source and target sentences, but have not tested yet
|-
|Shiyue Zhang || || || ||

|-
|Guli ||9:10||21:10||12 ||
*voice tagging
*write survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/22
|Andy Zhang||9:20 || 18:30 || 8+ ||
*decided to make some revises on bleu scoring part

|-
|Shiyue Zhang || 9:30 || 19:00|| 8+||
* try to change the scales of one-hot vec, and find >=-5000 is good
|-
|Guli ||9:20 ||21:10 ||11+ ||
*voice tagging
*write survey
|-
|Peilun Xiao ||9:20 || 19:00|| 9 ||
*read paper
*try to solve the bug
|-
| rowspan="4"|2016/12/23
|Andy Zhang||9:30 || 18:10 || 7+ ||
*finished bleu scoring part
*made it process by batches & testing several checkpoints and save the best one
|-
|Shiyue Zhang || 14:30 || 19:00|| 5.5 ||
* review the work of the whole week and discuss with teachers
* try joint training
|-
|Guli ||9:20|| 21:30 ||12+ ||
*voice tagging
*write survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/26
|Andy Zhang|| || || ||

|-
|Shiyue Zhang || 9:30 || 19:00|| 8+ ||
* weekly report
|-
|Guli ||9:10 || 21:30 ||12+ ||
* weekly report
* read pepar
|-
|Peilun Xiao || 9:20 ||19:00 ||8+ ||
* debug code
* read sklearn source code
|-
| rowspan="4"|2016/12/27
|Andy Zhang||9:30 || 18:30 || 8 ||
*modified the BLEU script to compare translation result with original sentences
|-
|Shiyue Zhang || 9:20 || 14:00|| 5.5 ||
*
|-
|Guli ||9:05||18:40 ||7+ ||
* read paper
* prepare data
|-
|Peilun Xiao ||9:20||19:00 ||9 ||
* debug code
* write a code about elm
|-
| rowspan="4"|2016/12/28
|Andy Zhang||9:30 || 18:30 || 8 ||
*modified BLEU script, now it is auto called while training
|-
|Shiyue Zhang || 9:20 || 19:00 || 8+ ||
* modify mem to the states before dropout
* update progress on CVSS
|-
|Guli ||9:30||15:30||6 ||
* bleu computation
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/29
|Andy Zhang||9:30 || 18:30 || 8 ||
*transferred to help Jiyuan with his work
*gathered 70+ poems for trainning
|-
|Shiyue Zhang || 9:10|| 17:10 || 7.5 ||
* pause the rnng work
* start to help Teacher Feng with NMT
|-
|Guli ||9:30||9:00 ||11+ ||
* prepare and run data
|-
|Peilun Xiao ||9:30 ||18:00 ||7+||
* prepare data
* run data
|-
| rowspan="4"|2016/12/30
|Andy Zhang|| || || ||

|-
|Shiyue Zhang || 9:30|| 19:10 || 8+ ||
* run the theano NMT code successfully
|-
|Guli ||9:30||21;30||12||
*
|-
|Peilun Xiao || || ||||

|-
|}

===Time Off Table===

{| class="wikitable"
! Date !! Yang Feng !! Jiyuan Zhang
|-
|}

==Past progress==

[[nlp-progress 2016/11]]

[[nlp-progress 2016/10]]

[[nlp-progress 2016/09]]

[[nlp-progress 2016/08]]

[[nlp-progress 2016/05/01 -- 08/16 | nlp-progress 2016/05-07]]

[[nlp-progress 2016/04]]

NLP Status Report 2017-1-3

2017-01-03T06:12:16Z

Guli：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
*[[nmt+mn:]] tried to improve the nmt baseline;
*read the code of Andy's;
*wrote the code for bleu evaluation;
*finished the code of nmt+mn;
*ran experiments;
||
*[[nmt+mn:]] do further experiments.
|-
|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
||
*improve poem 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 [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/9f/RNNG%2Bmm_experiment_report.pdf 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
|}

NLP Status Report 2017-1-3

2017-01-03T06:10:13Z

Guli：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
*[[nmt+mn:]] tried to improve the nmt baseline;
*read the code of Andy's;
*wrote the code for bleu evaluation;
*finished the code of nmt+mn;
*ran experiments;
||
*[[nmt+mn:]] do further experiments.
|-
|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
||
*improve poem 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 [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/9f/RNNG%2Bmm_experiment_report.pdf 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
* learn about tensorflow
* read papers
||
* 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
|}

NLP Status Report 2017-1-3

2017-01-03T06:09:45Z

Guli：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2016/12/26
|Yang Feng ||
*[[nmt+mn:]] tried to improve the nmt baseline;
*read the code of Andy's;
*wrote the code for bleu evaluation;
*finished the code of nmt+mn;
*ran experiments;
||
*[[nmt+mn:]] do further experiments.
|-
|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
||
*improve poem 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 [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/9f/RNNG%2Bmm_experiment_report.pdf 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
* learn about tensorflow
* read papers
||
* 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
|}

Schedule

2016-12-30T01:20:29Z

Guli：/* Daily Report */

=NLP Schedule=

==Members==

===Current Members===

* Yang Feng (冯洋)
* Jiyuan Zhang （张记袁）
* Aodong Li (李傲冬)
* Andi Zhang (张安迪)
* Shiyue Zhang (张诗悦)
* Li Gu (古丽)
* Peilun Xiao (肖培伦)

===Former Members===
* '''Chao Xing (邢超)''' : FreeNeb
* '''Rong Liu (刘荣)''' : 优酷
* '''Xiaoxi Wang (王晓曦)''' : 图灵机器人
* '''Xi Ma (马习)''' : 清华大学研究生
* '''Tianyi Luo (骆天一)''' ： phd candidate in University of California Santa Cruz
* '''Qixin Wang (王琪鑫)''' : MA candidate in University of California
* '''DongXu Zhang (张东旭)''': --
* '''Yiqiao Pan (潘一桥)''' ： MA candidate in University of Sydney
* '''Shiyao Li （李诗瑶）''' : BUPT
* '''Aiting Liu (刘艾婷)''' : BUPT

==Work Progress==
===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="3"|2016/12/1
|Andy Zhang|| 9:30||18:30 ||8 ||
*read source code
*thought about ways to store encoder output
|-
|Shiyue Zhang || 9:10 || 19:00|| 8+ ||
* draw tsne pictures
|-
|Guli ||9:10 ||9:50 ||12+ ||
*prepare data and run code
*prepare for Thesis Report
|-
| rowspan="4"|2016/12/2
|Andy Zhang|| 9:30|| 18:30|| 8||
*finish the code to output encoder output but have not tested yet
*prepared a small data set for testing
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||18:05 ||8 ||
*read code and check data
*think about how to improve bleu score
|-
|Peilun Xiao ||10:00||12:30|| 2+||
*learn basic things of work
|-
| rowspan="4"|2016/12/5
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*group meeting
*prepare the same data set as in Theano for Tensorflow
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+||
* discuss with teachers about the tsne pictures
* group meeting
|-
|Guli ||9:00 ||22:35 ||13+ ||
*install moses
*weekly report
|-
|Peilun Xiao ||9:30||18:30 ||8||
*learn how to use weka
|-
| rowspan="4"|2016/12/6
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*run fr-en (single encoder)
*prepare paraphrase data set, enumerate them, excluding 呀啊哈, etc.
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||22;30 ||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao ||9:40||18:30|| 8||
*read a paper
*use weka
|-
| rowspan="4"|2016/12/7
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*prepare paraphrase data set, enumerate them, excluding 呀啊哈, etc.
*met with some problems, used too much memory, had to restrict enumerate nums to 15000
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+||
* change mem to 28-dim states
* retry previous experiments
|-
|Guli ||9:15||22;00||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/8
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*finished preparing the data set
*start working on bidirectional model
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+||
* try more experiments, but all are not good, always converge to baseline
* draw the tsne picture of test data
* discuss with Teacher Wang
|-
|Guli ||9:15||21;15||12 ||
*run moses
*write Thesis Report
|-
|Peilun Xiao ||9:30||17:30|| 7||
*learn GibbsLda++
|-
| rowspan="4"|2016/12/9
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*finished coding, added masks for encoder inputs
*had a some breakthrough with Jiyuan's help, but still meet nan problem
|-
|Shiyue Zhang ||9:30 || 19:00 || 8+||
* return to 384-dim mem, which has 0.07 improvement than baseline
* replace cos with a one-layer neural network, which is also slightly better than baseline
* discuss with teachers, and find the problem of scale
|-
|Guli ||9:15||21;30||12 +||
*prepared Thesis Report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/12
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||10:00||19;00|| 9||
*read paper to solve oov
|-
|Peilun Xiao ||9:30||19:00||8+||
*use lda to generate document vector
|-
| rowspan="4"|2016/12/13
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*tried to modify the wrong softmax
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+ ||
* change mem scale to (0, -10000.0...)
* try previous experiments
|-
|Guli ||09:30||21;00||11+||
*read papers
|-
|Peilun Xiao ||9:50 ||19:00 || 8 ||
*use lda to generate document vector
|-
| rowspan="4"|2016/12/14
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*tried to modify the wrong softmax
*decided to abandon it for now
|-
|Shiyue Zhang || || || ||
|-
|Guli ||09:20||20;30||11+||
*read papers
*writing a survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/15
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*tried to add bleu scoring into the code, but met with out of memory problem
|-
|Shiyue Zhang || 9:30 || 19:00|| 8+||
* changed scale didn't lead to better results
* try 1-dim gate, but converge to baseline
|-
|Guli ||09:20||20;30||11+||
*read papers
*writing a survey
|-
|Peilun Xiao ||13:30||19:00||5+||
*use lda to generate document vector
|-
| rowspan="4"|2016/12/16
|Andy Zhang|| 9:20 || 18:20 || 8 ||
*finished adding bleu scoring into the code
|-
|Shiyue Zhang || 14:00 || 19:00|| 5||
* try to only train gate
* try model similar to attention
|-
|Guli ||09:30||20;30||11||
*Check the data, modify the error
*writing a survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/19
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*group meeting
*made some revises on bleu scoring
|-
|Shiyue Zhang || 9:00 || 19:00|| 9||
* review last week work
* write the report and talk with teachers
* decide what to do next and meeting
* try to train gate with true action info
|-
|Guli ||9:15||20:00||10+||
*weekly meeting
*conduct comparative test
|-
|Peilun Xiao ||9:30 ||19:00 || 8+ ||
*weekly meeting
*code on tf-idf
|-
| rowspan="4"|2016/12/20
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*dealt with some bugs on bidirectional model
*coding on getting encoder outputs
|-
|Shiyue Zhang || 9:30 ||19:00|| 8+||
* try to train gate with true actions, which gets the results better than no true action, but still not very good.
* try to change cos to inner product, which gets better performance than cos.
|-
|Guli ||9:00||21:50||12+||
*voice tagging
*write survey
|-
|Peilun Xiao ||9:50||18:30 ||8 ||
*debug the code
*prepare a small test set
|-
| rowspan="4"|2016/12/21
|Andy Zhang||9:20 || 18:30 || 8+ ||
*finishing testing on getting encoder outputs
*coded to output corresponding source and target sentences, but have not tested yet
|-
|Shiyue Zhang || || || ||

|-
|Guli ||9:10||21:10||12 ||
*voice tagging
*write survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/22
|Andy Zhang||9:20 || 18:30 || 8+ ||
*decided to make some revises on bleu scoring part

|-
|Shiyue Zhang || 9:30 || 19:00|| 8+||
* try to change the scales of one-hot vec, and find >=-5000 is good
|-
|Guli ||9:20 ||21:10 ||11+ ||
*voice tagging
*write survey
|-
|Peilun Xiao ||9:20 || 19:00|| 9 ||
*read paper
*try to solve the bug
|-
| rowspan="4"|2016/12/23
|Andy Zhang||9:30 || 18:10 || 7+ ||
*finished bleu scoring part
*made it process by batches & testing several checkpoints and save the best one
|-
|Shiyue Zhang || 14:30 || 19:00|| 5.5 ||
* review the work of the whole week and discuss with teachers
* try joint training
|-
|Guli ||9:20|| 21:30 ||12+ ||
*voice tagging
*write survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/26
|Andy Zhang|| || || ||

|-
|Shiyue Zhang || 14:30 || 19:00|| 5.5 ||
*
|-
|Guli ||9:10 || 21:30 ||12+ ||
* weekly report
* read pepar
|-
|Peilun Xiao || 9:20 ||19:00 ||8+ ||
* debug code
* read sklearn source code
|-
| rowspan="4"|2016/12/27
|Andy Zhang||9:30 || 18:30 || 8 ||
*modified the BLEU script to compare translation result with original sentences
|-
|Shiyue Zhang || 14:30 || 19:00|| 5.5 ||
*
|-
|Guli ||9:05||18:40 ||7+ ||
* read paper
* prepare data
|-
|Peilun Xiao ||9:20||19:00 ||9 ||
* debug code
* write a code about elm
|-
| rowspan="4"|2016/12/28
|Andy Zhang||9:30 || 18:30 || 8 ||
*modified BLEU script, now it is auto called while training
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:30||15:30||6 ||
* bleu computation
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/29
|Andy Zhang||9:30 || 18:30 || 8 ||

|-
|Shiyue Zhang || || || ||

|-
|Guli ||9:30||9:00 ||11+ ||
* prepare and run data
|-
|Peilun Xiao ||9:30 ||18:00 ||7+||
* prepare data
* run data
|-
|}

===Time Off Table===

{| class="wikitable"
! Date !! Yang Feng !! Jiyuan Zhang
|-
|}

==Past progress==

[[nlp-progress 2016/11]]

[[nlp-progress 2016/10]]

[[nlp-progress 2016/09]]

[[nlp-progress 2016/08]]

[[nlp-progress 2016/05/01 -- 08/16 | nlp-progress 2016/05-07]]

[[nlp-progress 2016/04]]

Schedule

2016-12-27T09:48:05Z

Guli：/* Daily Report */

=NLP Schedule=

==Members==

===Current Members===

* Yang Feng (冯洋)
* Jiyuan Zhang （张记袁）
* Aodong Li (李傲冬)
* Andi Zhang (张安迪)
* Shiyue Zhang (张诗悦)
* Li Gu (古丽)
* Peilun Xiao (肖培伦)

===Former Members===
* '''Chao Xing (邢超)''' : FreeNeb
* '''Rong Liu (刘荣)''' : 优酷
* '''Xiaoxi Wang (王晓曦)''' : 图灵机器人
* '''Xi Ma (马习)''' : 清华大学研究生
* '''Tianyi Luo (骆天一)''' ： phd candidate in University of California Santa Cruz
* '''Qixin Wang (王琪鑫)''' : MA candidate in University of California
* '''DongXu Zhang (张东旭)''': --
* '''Yiqiao Pan (潘一桥)''' ： MA candidate in University of Sydney
* '''Shiyao Li （李诗瑶）''' : BUPT
* '''Aiting Liu (刘艾婷)''' : BUPT

==Work Progress==
===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="3"|2016/12/1
|Andy Zhang|| 9:30||18:30 ||8 ||
*read source code
*thought about ways to store encoder output
|-
|Shiyue Zhang || 9:10 || 19:00|| 8+ ||
* draw tsne pictures
|-
|Guli ||9:10 ||9:50 ||12+ ||
*prepare data and run code
*prepare for Thesis Report
|-
| rowspan="4"|2016/12/2
|Andy Zhang|| 9:30|| 18:30|| 8||
*finish the code to output encoder output but have not tested yet
*prepared a small data set for testing
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||18:05 ||8 ||
*read code and check data
*think about how to improve bleu score
|-
|Peilun Xiao ||10:00||12:30|| 2+||
*learn basic things of work
|-
| rowspan="4"|2016/12/5
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*group meeting
*prepare the same data set as in Theano for Tensorflow
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+||
* discuss with teachers about the tsne pictures
* group meeting
|-
|Guli ||9:00 ||22:35 ||13+ ||
*install moses
*weekly report
|-
|Peilun Xiao ||9:30||18:30 ||8||
*learn how to use weka
|-
| rowspan="4"|2016/12/6
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*run fr-en (single encoder)
*prepare paraphrase data set, enumerate them, excluding 呀啊哈, etc.
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||22;30 ||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao ||9:40||18:30|| 8||
*read a paper
*use weka
|-
| rowspan="4"|2016/12/7
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*prepare paraphrase data set, enumerate them, excluding 呀啊哈, etc.
*met with some problems, used too much memory, had to restrict enumerate nums to 15000
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+||
* change mem to 28-dim states
* retry previous experiments
|-
|Guli ||9:15||22;00||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/8
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*finished preparing the data set
*start working on bidirectional model
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+||
* try more experiments, but all are not good, always converge to baseline
* draw the tsne picture of test data
* discuss with Teacher Wang
|-
|Guli ||9:15||21;15||12 ||
*run moses
*write Thesis Report
|-
|Peilun Xiao ||9:30||17:30|| 7||
*learn GibbsLda++
|-
| rowspan="4"|2016/12/9
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*finished coding, added masks for encoder inputs
*had a some breakthrough with Jiyuan's help, but still meet nan problem
|-
|Shiyue Zhang ||9:30 || 19:00 || 8+||
* return to 384-dim mem, which has 0.07 improvement than baseline
* replace cos with a one-layer neural network, which is also slightly better than baseline
* discuss with teachers, and find the problem of scale
|-
|Guli ||9:15||21;30||12 +||
*prepared Thesis Report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/12
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||10:00||19;00|| 9||
*read paper to solve oov
|-
|Peilun Xiao ||9:30||19:00||9+||
*use lda to generate document vector
|-
| rowspan="4"|2016/12/13
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*tried to modify the wrong softmax
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+ ||
* change mem scale to (0, -10000.0...)
* try previous experiments
|-
|Guli ||09:30||21;00||11+||
*read papers
|-
|Peilun Xiao ||9:50 ||19:00 || 9 ||
*use lda to generate document vector
|-
| rowspan="4"|2016/12/14
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*tried to modify the wrong softmax
*decided to abandon it for now
|-
|Shiyue Zhang || || || ||
|-
|Guli ||09:20||20;30||11+||
*read papers
*writing a survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/15
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*tried to add bleu scoring into the code, but met with out of memory problem
|-
|Shiyue Zhang || 9:30 || 19:00|| 8+||
* changed scale didn't lead to better results
* try 1-dim gate, but converge to baseline
|-
|Guli ||09:20||20;30||11+||
*read papers
*writing a survey
|-
|Peilun Xiao ||13:30||19:00||5+||
*use lda to generate document vector
|-
| rowspan="4"|2016/12/16
|Andy Zhang|| 9:20 || 18:20 || 8 ||
*finished adding bleu scoring into the code
|-
|Shiyue Zhang || 14:00 || 19:00|| 5||
* try to only train gate
* try model similar to attention
|-
|Guli ||09:30||20;30||11||
*Check the data, modify the error
*writing a survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/19
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*group meeting
*made some revises on bleu scoring
|-
|Shiyue Zhang || 9:00 || 19:00|| 9||
* review last week work
* write the report and talk with teachers
* decide what to do next and meeting
* try to train gate with true action info
|-
|Guli ||9：15||20：00||10+||
*weekly meeting
*conduct comparative test
|-
|Peilun Xiao ||9：30 ||19：00 || 9+ ||
*weekly meeting
*code on tf-idf
|-
| rowspan="4"|2016/12/20
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*dealt with some bugs on bidirectional model
*coding on getting encoder outputs
|-
|Shiyue Zhang || 9:30 ||19:00|| 8+||
* try to train gate with true actions, which gets the results better than no true action, but still not very good.
* try to change cos to inner product, which gets better performance than cos.
|-
|Guli ||9：00||21：50||12+||
*voice tagging
*write survey
|-
|Peilun Xiao ||9:50||18:30 ||8 ||
*debug the code
*prepare a small test set
|-
| rowspan="4"|2016/12/21
|Andy Zhang||9:20 || 18:30 || 8+ ||
*finishing testing on getting encoder outputs
*coded to output corresponding source and target sentences, but have not tested yet
|-
|Shiyue Zhang || || || ||

|-
|Guli ||9：10||21：10 ||12 ||
*voice tagging
*write survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/22
|Andy Zhang||9:20 || 18:30 || 8+ ||
*decided to make some revises on bleu scoring part

|-
|Shiyue Zhang || 9:30 || 19:00|| 8+||
* try to change the scales of one-hot vec, and find >=-5000 is good
|-
|Guli ||9：20 ||21:10 ||11+ ||
*voice tagging
*write survey
|-
|Peilun Xiao ||9:20 || 19:00|| 9 ||
*read paper
*try to solve the bug
|-
| rowspan="4"|2016/12/23
|Andy Zhang||9:30 || 18:10 || 7+ ||
*finished bleu scoring part
*made it process by batches & testing several checkpoints and save the best one
|-
|Shiyue Zhang || 14:30 || 19:00|| 5.5 ||
* review the work of the whole week and discuss with teachers
* try joint training
|-
|Guli ||9：20|| 21:30 ||12+ ||
*voice tagging
*write survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/26
|Andy Zhang||9:30 || 18:10 || 7+ ||
*
|-
|Shiyue Zhang || 14:30 || 19:00|| 5.5 ||
*
|-
|Guli ||9:10 || 21:30 ||12+ ||
* weekly report
* read pepar
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/27
|Andy Zhang||9:30 || 18:10 || 7+ ||
*
|-
|Shiyue Zhang || 14:30 || 19:00|| 5.5 ||
*
|-
|Guli ||9：05||18:40 ||7+ ||
* read paper
* prepare data
|-
|Peilun Xiao || || || ||
|-
|}

===Time Off Table===

{| class="wikitable"
! Date !! Yang Feng !! Jiyuan Zhang
|-
|}

==Past progress==

[[nlp-progress 2016/11]]

[[nlp-progress 2016/10]]

[[nlp-progress 2016/09]]

[[nlp-progress 2016/08]]

[[nlp-progress 2016/05/01 -- 08/16 | nlp-progress 2016/05-07]]

[[nlp-progress 2016/04]]

Asr-nsfc-weekly-2016-12-26

2016-12-26T11:22:28Z

Guli：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="5"|2016.12.26
|-
|清华
||
*新AM训练完毕，使用网上抓取的数据做了新的LM但是所抓取内容是否有实际意义，有没有抓错无法验证。
||
* 写哈萨克语的TRP
|-
|-
|新大
||
* 通过两次会议，确定了哈语的音节规则，并根据音节规则检查拼写。发现并更正100多个拼写错误。
||
* 20万句子的拼写纠错及发音辞典的建立。
|-
|-
|民大
||
* 完成藏语拉萨话口语翻译800句。
||
* 分别准备藏语及蒙语书面语发音文本9万句和6万句。
|-
|}
------------------------------------------------------------------------------------------------------------
{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="5"|2016.12.19
|-
|清华
||
* 通过爬虫爬取了 http://www.elarna.com/tote.php 和 http://kazakh.people.com.cn/ 中的一些数据，完成了爬取语料的处理工作
||
* 针对重新补录的数据集重新训练AM模型，使用网络爬取的语料和处理过的翻译局提供的语料生成LM。
|-
|-
|新大
||
* We collected a Chinese-Russian-Kazak parallel corpus of dialog, which, we think, is free from spelling mistakes.
||
* Keep working on Kazak acousic dictionary tool, which has not been finished.
|-
|-
|民大
||
* 完成藏语拉萨话发音词典的校对
* 藏语口语发音文本翻译完成500句
||
* 藏语和蒙语书面发音文本的选择
* 口语发音文本翻译
|-
|}

Asr-nsfc-weekly-2016-12-26

2016-12-26T11:21:39Z

Guli：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="5"|2016.12.26
|-
|清华
||
*新AM训练完毕，使用网上抓取的数据做了新的LM但是所抓取内容是否有实际意义，有没有抓错无法验证。
||
* 写哈萨克语的TRP
|-
|-
|新大
||
* 通过两次会议，确定了哈语的音节规则，并根据音节规则的检查拼写。发现并更正100多个拼写错误。
||
* 20万句子的拼写纠错及发音辞典的建立。
|-
|-
|民大
||
* 完成藏语拉萨话口语翻译800句。
||
* 分别准备藏语及蒙语书面语发音文本9万句和6万句。
|-
|}
------------------------------------------------------------------------------------------------------------
{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="5"|2016.12.19
|-
|清华
||
* 通过爬虫爬取了 http://www.elarna.com/tote.php 和 http://kazakh.people.com.cn/ 中的一些数据，完成了爬取语料的处理工作
||
* 针对重新补录的数据集重新训练AM模型，使用网络爬取的语料和处理过的翻译局提供的语料生成LM。
|-
|-
|新大
||
* We collected a Chinese-Russian-Kazak parallel corpus of dialog, which, we think, is free from spelling mistakes.
||
* Keep working on Kazak acousic dictionary tool, which has not been finished.
|-
|-
|民大
||
* 完成藏语拉萨话发音词典的校对
* 藏语口语发音文本翻译完成500句
||
* 藏语和蒙语书面发音文本的选择
* 口语发音文本翻译
|-
|}

Asr-nsfc-weekly-2016-12-26

2016-12-26T05:54:01Z

Guli：

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="5"|2016.12.19
|-
|清华
||
*新AM训练完毕，使用网上抓取的数据做了新的LM但是所抓取内容是否有实际意义，有没有抓错无法验证。
||
* 写哈萨克语的TRP
|-
|-
|新大
||
*
||
*
|-
|-
|民大
||
* 完成藏语拉萨话口语翻译800句。
||
* 分别准备藏语及蒙语书面语发音文本9万句和6万句。
|-
|}
------------------------------------------------------------------------------------------------------------
{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="5"|2016.12.19
|-
|清华
||
* 通过爬虫爬取了 http://www.elarna.com/tote.php 和 http://kazakh.people.com.cn/ 中的一些数据，完成了爬取语料的处理工作
||
* 针对重新补录的数据集重新训练AM模型，使用网络爬取的语料和处理过的翻译局提供的语料生成LM。
|-
|-
|新大
||
* We collected a Chinese-Russian-Kazak parallel corpus of dialog, which, we think, is free from spelling mistakes.
||
* Keep working on Kazak acousic dictionary tool, which has not been finished.
|-
|-
|民大
||
* 完成藏语拉萨话发音词典的校对
* 藏语口语发音文本翻译完成500句
||
* 藏语和蒙语书面发音文本的选择
* 口语发音文本翻译
|-
|}

文件:Semi-Supervised Learning for Neural Machine Translation.pdf

2016-12-26T05:16:02Z

Guli：

NLP Status Report 2016-12-26

2016-12-26T05:01:15Z

Guli：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2016/12/26
|Yang Feng ||
*[[s2smn:]] read six papers to fix the details of our model;
*wrote the proposal of lexical memory and discussed the details with Teach Wang;
*finished coding of only adding attention to the decoder and under debugging;
*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]] ;
*prepare the dictionary for the memory loading;
*[[Huilan:]] documentation
||
*[[s2smn:]] run the ecperiments.
*[[rnng+mn:]] try to find the problem.
|-
|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][http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/05/Five_local_attention.pdf five]generated by local_attention model
||
*improve poem model
|-
|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.
* [[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
* 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
|}

Schedule

2016-12-26T00:49:46Z

Guli：/* Daily Report */

=NLP Schedule=

==Members==

===Current Members===

* Yang Feng (冯洋)
* Jiyuan Zhang （张记袁）
* Aodong Li (李傲冬)
* Andi Zhang (张安迪)
* Shiyue Zhang (张诗悦)
* Li Gu (古丽)
* Peilun Xiao (肖培伦)

===Former Members===
* '''Chao Xing (邢超)''' : FreeNeb
* '''Rong Liu (刘荣)''' : 优酷
* '''Xiaoxi Wang (王晓曦)''' : 图灵机器人
* '''Xi Ma (马习)''' : 清华大学研究生
* '''Tianyi Luo (骆天一)''' ： phd candidate in University of California Santa Cruz
* '''Qixin Wang (王琪鑫)''' : MA candidate in University of California
* '''DongXu Zhang (张东旭)''': --
* '''Yiqiao Pan (潘一桥)''' ： MA candidate in University of Sydney
* '''Shiyao Li （李诗瑶）''' : BUPT
* '''Aiting Liu (刘艾婷)''' : BUPT

==Work Progress==
===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="3"|2016/12/1
|Andy Zhang|| 9:30||18:30 ||8 ||
*read source code
*thought about ways to store encoder output
|-
|Shiyue Zhang || 9:10 || 19:00|| 8+ ||
* draw tsne pictures
|-
|Guli ||9:10 ||9:50 ||12+ ||
*prepare data and run code
*prepare for Thesis Report
|-
| rowspan="4"|2016/12/2
|Andy Zhang|| 9:30|| 18:30|| 8||
*finish the code to output encoder output but have not tested yet
*prepared a small data set for testing
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||18:05 ||8 ||
*read code and check data
*think about how to improve bleu score
|-
|Peilun Xiao ||10:00||12:30|| 2+||
*learn basic things of work
|-
| rowspan="4"|2016/12/5
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*group meeting
*prepare the same data set as in Theano for Tensorflow
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+||
* discuss with teachers about the tsne pictures
* group meeting
|-
|Guli ||9:00 ||22:35 ||13+ ||
*install moses
*weekly report
|-
|Peilun Xiao ||9:30||18:30 ||8||
*learn how to use weka
|-
| rowspan="4"|2016/12/6
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*run fr-en (single encoder)
*prepare paraphrase data set, enumerate them, excluding 呀啊哈, etc.
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||22;30 ||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao ||9:40||18:30|| 8||
*read a paper
*use weka
|-
| rowspan="4"|2016/12/7
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*prepare paraphrase data set, enumerate them, excluding 呀啊哈, etc.
*met with some problems, used too much memory, had to restrict enumerate nums to 15000
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+||
* change mem to 28-dim states
* retry previous experiments
|-
|Guli ||9:15||22;00||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/8
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*finished preparing the data set
*start working on bidirectional model
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+||
* try more experiments, but all are not good, always converge to baseline
* draw the tsne picture of test data
* discuss with Teacher Wang
|-
|Guli ||9:15||21;15||12 ||
*run moses
*write Thesis Report
|-
|Peilun Xiao ||9:30||17:30|| 7||
*learn GibbsLda++
|-
| rowspan="4"|2016/12/9
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*finished coding, added masks for encoder inputs
*had a some breakthrough with Jiyuan's help, but still meet nan problem
|-
|Shiyue Zhang ||9:30 || 19:00 || 8+||
* return to 384-dim mem, which has 0.07 improvement than baseline
* replace cos with a one-layer neural network, which is also slightly better than baseline
* discuss with teachers, and find the problem of scale
|-
|Guli ||9:15||21;30||12 +||
*prepared Thesis Report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/12
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||10:00||19;00|| 9||
*read paper to solve oov
|-
|Peilun Xiao ||9:30||19:00||9+||
*use lda to generate document vector
|-
| rowspan="4"|2016/12/13
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*tried to modify the wrong softmax
|-
|Shiyue Zhang || 9:30 || 19:00 || 8+ ||
* change mem scale to (0, -10000.0...)
* try previous experiments
|-
|Guli ||09:30||21;00||11+||
*read papers
|-
|Peilun Xiao ||9:50 ||19:00 || 9 ||
*use lda to generate document vector
|-
| rowspan="4"|2016/12/14
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*tried to modify the wrong softmax
*decided to abandon it for now
|-
|Shiyue Zhang || || || ||
|-
|Guli ||09:20||20;30||11+||
*read papers
*writing a survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/15
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*tried to add bleu scoring into the code, but met with out of memory problem
|-
|Shiyue Zhang || 9:30 || 19:00|| 8+||
* changed scale didn't lead to better results
* try 1-dim gate, but converge to baseline
|-
|Guli ||09:20||20;30||11+||
*read papers
*writing a survey
|-
|Peilun Xiao ||13:30||19:00||5+||
*use lda to generate document vector
|-
| rowspan="4"|2016/12/16
|Andy Zhang|| 9:20 || 18:20 || 8 ||
*finished adding bleu scoring into the code
|-
|Shiyue Zhang || 14:00 || 19:00|| 5||
* try to only train gate
* try model similar to attention
|-
|Guli ||09:30||20;30||11||
*Check the data, modify the error
*writing a survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/19
|Andy Zhang|| 9:30 || 18:30 || 8 ||
*group meeting
*made some revises on bleu scoring
|-
|Shiyue Zhang || 9:00 || 19:00|| 9||
* review last week work
* write the report and talk with teachers
* decide what to do next and meeting
* try to train gate with true action info
|-
|Guli ||9：15||20：00||10+||
*weekly meeting
*conduct comparative test
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/20
|Andy Zhang|| 9:30 || 19:00 || 8+ ||
*dealt with some bugs on bidirectional model
*coding on getting encoder outputs
|-
|Shiyue Zhang || |||| ||

|-
|Guli ||9：00||21：50||12+||
*voice tagging
*write survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/21
|Andy Zhang||9:20 || 18:30 || 8+ ||
*finishing testing on getting encoder outputs
*coded to output corresponding source and target sentences, but have not tested yet
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9：10||21：10 ||12 ||
*voice tagging
*write survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/22
|Andy Zhang||9:20 || 18:30 || 8+ ||
*finishing testing on getting encoder outputs
*coded to output corresponding source and target sentences, but have not tested yet
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9：20 ||21:10 ||11+ ||
*voice tagging
*write survey
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/23
|Andy Zhang||9:20 || || ||
*finishing testing on getting encoder outputs
*coded to output corresponding source and target sentences, but have not tested yet
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9：20|| 21:30 ||12+ ||
*voice tagging
*write survey
|-
|Peilun Xiao || || || ||
|-
|}

===Time Off Table===

{| class="wikitable"
! Date !! Yang Feng !! Jiyuan Zhang
|-
|}

==Past progress==

[[nlp-progress 2016/11]]

[[nlp-progress 2016/10]]

[[nlp-progress 2016/09]]

[[nlp-progress 2016/08]]

[[nlp-progress 2016/05/01 -- 08/16 | nlp-progress 2016/05-07]]

[[nlp-progress 2016/04]]

Schedule

2016-12-21T04:13:07Z

Guli：/* Daily Report */

NLP Status Report 2016-12-19

2016-12-19T05:23:12Z

Guli：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| 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]]
*wrote part of the code of mn.
*wrote the manual of Moses [[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 moses-manual]]
*[[Huilan:]] fixed the problem of syntax-based translation.
*sort out the system and corresponding documents.
||
*[[s2smn:]] finish the code of adding mn.
*[[Huilan:]] handover.
|-
|Jiyuan Zhang ||
*attempted to use memory model to improve the atten model of bad effect
*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]
*Modified working mechanism of memory model(top1 to average)
*help andi
||
*improve poem model
|-
|Andi Zhang ||
*prepared a paraphrase data set that is enumerated from a previous one (ignoring words like "啊呀哈")
*worked on coding bidirectional model under tensorflow, met with NAN problem
||
*ignore NAN problem for now, run it on the same data set used in Theano
|-
|Shiyue Zhang ||
* changed the one-hot vector to (0, -inf, -inf...), and retied the experiments. But no improvement showed.
* tried 1-dim gate, but converged to baseline
* 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/9/9f/RNNG%2Bmm_experiment_report.pdf report]]
||
* try to add true action info when training gate
* try different scale vectors
* try to change cos to only inner product
|-
|Guli ||
*read papers about Transfer learning and solving OOV
*conducted comparative test
*writing survey
||
* complete the first draft of the survey
|-
|Peilun Xiao ||
*Read a paper about document classification wiht GMM distributions of word vecotrs and try to code it in python
*Use LDA to reduce the dimension of the text in r52、r8 and contrast the performance of classification
||
*Use LDA to reduce the dimension of the text in 20news and webkb
|}

Schedule

2016-12-18T11:26:59Z

Guli：/* Daily Report */

Schedule

2016-12-15T11:59:30Z

Guli：/* Work Progress */

Schedule

2016-12-13T12:17:28Z

Guli：/* Daily Report */

NLP Status Report 2016-12-12

2016-12-13T09:35:18Z

Guli：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="5"|2016/12/05
|Yang Feng ||
*[[s2smn:]] installed tensorflow and ran a toy example (solved problems: version conflict and memory exhausted)
*wrote the code of the memory network part
*[[Huilan:]] prepared for periodical report and system submission.
||
*[[s2smn:]] finish the code of mn
*[[poemgen:]] experiment design
*[[Huilan:]] system submission
|-
|Jiyuan Zhang ||
*attempted to use memory model to improve the atten model of bad effect
*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]
*Modified working mechanism of memory model(top1 to average)
*help andi
||
*improve poem model
|-
|Andi Zhang ||
||

|-
|Shiyue Zhang ||
||
|-
|Guli ||
*install and run moses
*prepare thesis report
||
*read papers about Transfer learning and solving OOV
|}

Schedule

2016-12-13T01:11:24Z

Guli：/* Daily Report */

Schedule

2016-12-12T07:02:51Z

Guli：/* Daily Report */

=NLP Schedule=

==Members==

===Current Members===

* Yang Feng (冯洋)
* Jiyuan Zhang （张记袁）
* Andi Zhang (张安迪)
* Shiyue Zhang (张诗悦)
* Li Gu (古丽)
* Peilun Xiao (肖培伦)

===Former Members===
* '''Chao Xing (邢超)''' : FreeNeb
* '''Rong Liu (刘荣)''' : 优酷
* '''Xiaoxi Wang (王晓曦)''' : 图灵机器人
* '''Xi Ma (马习)''' : 清华大学研究生
* '''Tianyi Luo (骆天一)''' ： phd candidate in University of California Santa Cruz
* '''Qixin Wang (王琪鑫)''' : MA candidate in University of California
* '''DongXu Zhang (张东旭)''': --
* '''Yiqiao Pan (潘一桥)''' ： MA candidate in University of Sydney
* '''Shiyao Li （李诗瑶）''' : BUPT
* '''Aiting Liu (刘艾婷)''' : BUPT
* '''Aodong Li (李傲冬)'''：BUPT

==Work Progress==
===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="3"|2016/12/1
|Andy Zhang|| 9:30||18:30 ||8 ||
*read source code
*thought about ways to store encoder output
|-
|Shiyue Zhang || 9:10 || 19:00|| 8+ ||
* draw tsne pictures
|-
|Guli ||9:10 ||9:50 ||12+ ||
*prepare data and run code
*prepare for Thesis Report
|-
| rowspan="4"|2016/12/2
|Andy Zhang|| 9:30|| 18:30|| 8||
*finish the code to output encoder output but have not tested yet
*prepared a small data set for testing
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||18:05 ||8 ||
*read code and check data
*think about how to improve bleu score
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/5
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:00 ||22:35 ||13+ ||
*install moses
*weekly report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/6
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||22;30 ||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/7
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:15||22;00||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/8
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:15||21;15||12 ||
*run moses
*write Thesis Report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/9
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:15||21;30||12 +||
*prepared Thesis Report
|-
|Peilun Xiao || || || ||
|-
|}

===Time Off Table===

{| class="wikitable"
! Date !! Yang Feng !! Jiyuan Zhang
|-
|}

==Past progress==

[[nlp-progress 2016/11]]

[[nlp-progress 2016/10]]

[[nlp-progress 2016/09]]

[[nlp-progress 2016/08]]

[[nlp-progress 2016/05/01 -- 08/16 | nlp-progress 2016/05-07]]

[[nlp-progress 2016/04]]

Schedule

2016-12-08T12:31:27Z

Guli：/* Daily Report */

=NLP Schedule=

==Members==

===Current Members===

* Yang Feng (冯洋)
* Jiyuan Zhang （张记袁）
* Andi Zhang (张安迪)
* Shiyue Zhang (张诗悦)
* Li Gu (古丽)
* Peilun Xiao (肖培伦)

===Former Members===
* '''Chao Xing (邢超)''' : FreeNeb
* '''Rong Liu (刘荣)''' : 优酷
* '''Xiaoxi Wang (王晓曦)''' : 图灵机器人
* '''Xi Ma (马习)''' : 清华大学研究生
* '''Tianyi Luo (骆天一)''' ： phd candidate in University of California Santa Cruz
* '''Qixin Wang (王琪鑫)''' : MA candidate in University of California
* '''DongXu Zhang (张东旭)''': --
* '''Yiqiao Pan (潘一桥)''' ： MA candidate in University of Sydney
* '''Shiyao Li （李诗瑶）''' : BUPT
* '''Aiting Liu (刘艾婷)''' : BUPT
* '''Aodong Li (李傲冬)'''：BUPT

==Work Progress==
===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="3"|2016/12/1
|Andy Zhang|| 9:30||18:30 ||8 ||
*read source code
*thought about ways to store encoder output
|-
|Shiyue Zhang || 9:10 || 19:00|| 8+ ||
* draw tsne pictures
|-
|Guli ||9:10 ||9:50 ||12+ ||
*prepare data and run code
*prepare for Thesis Report
|-
| rowspan="4"|2016/12/2
|Andy Zhang|| 9:30|| 18:30|| 8||
*finish the code to output encoder output but have not tested yet
*prepared a small data set for testing
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||18:05 ||8 ||
*read code and check data
*think about how to improve bleu score
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/5
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:00 ||22:35 ||13+ ||
*install moses
*weekly report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/6
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||22;30 ||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/7
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:15||22;00||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/8
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:15||21;15||12 ||
*run moses
*write Thesis Report
|-
|Peilun Xiao || || || ||
|-
|}

===Time Off Table===

{| class="wikitable"
! Date !! Yang Feng !! Jiyuan Zhang
|-
|}

==Past progress==

[[nlp-progress 2016/11]]

[[nlp-progress 2016/10]]

[[nlp-progress 2016/09]]

[[nlp-progress 2016/08]]

[[nlp-progress 2016/05/01 -- 08/16 | nlp-progress 2016/05-07]]

[[nlp-progress 2016/04]]

Schedule

2016-12-07T13:07:42Z

Guli：/* Daily Report */

=NLP Schedule=

==Members==

===Current Members===

* Yang Feng (冯洋)
* Jiyuan Zhang （张记袁）
* Andi Zhang (张安迪)
* Shiyue Zhang (张诗悦)
* Li Gu (古丽)
* Peilun Xiao (肖培伦)

===Former Members===
* '''Chao Xing (邢超)''' : FreeNeb
* '''Rong Liu (刘荣)''' : 优酷
* '''Xiaoxi Wang (王晓曦)''' : 图灵机器人
* '''Xi Ma (马习)''' : 清华大学研究生
* '''Tianyi Luo (骆天一)''' ： phd candidate in University of California Santa Cruz
* '''Qixin Wang (王琪鑫)''' : MA candidate in University of California
* '''DongXu Zhang (张东旭)''': --
* '''Yiqiao Pan (潘一桥)''' ： MA candidate in University of Sydney
* '''Shiyao Li （李诗瑶）''' : BUPT
* '''Aiting Liu (刘艾婷)''' : BUPT
* '''Aodong Li (李傲冬)'''：BUPT

==Work Progress==
===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="3"|2016/12/1
|Andy Zhang|| 9:30||18:30 ||8 ||
*read source code
*thought about ways to store encoder output
|-
|Shiyue Zhang || 9:10 || 19:00|| 8+ ||
* draw tsne pictures
|-
|Guli ||9:10 ||9:50 ||12+ ||
*prepare data and run code
*prepare for Thesis Report
|-
| rowspan="4"|2016/12/2
|Andy Zhang|| 9:30|| 18:30|| 8||
*finish the code to output encoder output but have not tested yet
*prepared a small data set for testing
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||18:05 ||8 ||
*read code and check data
*think about how to improve bleu score
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/5
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:00 ||22:35 ||13+ ||
*install moses
*weekly report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/6
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||22;30 ||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/7
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:15||22;00||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao || || || ||
|-
|}

===Time Off Table===

{| class="wikitable"
! Date !! Yang Feng !! Jiyuan Zhang
|-
|}

==Past progress==

[[nlp-progress 2016/11]]

[[nlp-progress 2016/10]]

[[nlp-progress 2016/09]]

[[nlp-progress 2016/08]]

[[nlp-progress 2016/05/01 -- 08/16 | nlp-progress 2016/05-07]]

[[nlp-progress 2016/04]]

Schedule

2016-12-06T10:35:08Z

Guli：/* Daily Report */

=NLP Schedule=

==Members==

===Current Members===

* Yang Feng (冯洋)
* Jiyuan Zhang （张记袁）
* Andi Zhang (张安迪)
* Shiyue Zhang (张诗悦)
* Li Gu (古丽)
* Peilun Xiao (肖培伦)

===Former Members===
* '''Chao Xing (邢超)''' : FreeNeb
* '''Rong Liu (刘荣)''' : 优酷
* '''Xiaoxi Wang (王晓曦)''' : 图灵机器人
* '''Xi Ma (马习)''' : 清华大学研究生
* '''Tianyi Luo (骆天一)''' ： phd candidate in University of California Santa Cruz
* '''Qixin Wang (王琪鑫)''' : MA candidate in University of California
* '''DongXu Zhang (张东旭)''': --
* '''Yiqiao Pan (潘一桥)''' ： MA candidate in University of Sydney
* '''Shiyao Li （李诗瑶）''' : BUPT
* '''Aiting Liu (刘艾婷)''' : BUPT
* '''Aodong Li (李傲冬)'''：BUPT

==Work Progress==
===Daily Report===

{|class="wikitable"
! Date !! Person !! start!! leave !! hours ||status
|-
| rowspan="3"|2016/12/1
|Andy Zhang|| 9:30||18:30 ||8 ||
*read source code
*thought about ways to store encoder output
|-
|Shiyue Zhang || 9:10 || 19:00|| 8+ ||
* draw tsne pictures
|-
|Guli ||9:10 ||9:50 ||12+ ||
*prepare data and run code
*prepare for Thesis Report
|-
| rowspan="4"|2016/12/2
|Andy Zhang|| 9:30|| 18:30|| 8||
*finish the code to output encoder output but have not tested yet
*prepared a small data set for testing
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||18:05 ||8 ||
*read code and check data
*think about how to improve bleu score
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/5
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:00 ||22:35 ||13+ ||
*install moses
*weekly report
|-
|Peilun Xiao || || || ||
|-
| rowspan="4"|2016/12/6
|Andy Zhang|| || || ||
|-
|Shiyue Zhang || || || ||
|-
|Guli ||9:05 ||23;30 ||12+ ||
*run moses
*write Thesis Report
|-
|Peilun Xiao || || || ||
|-
|}

===Time Off Table===

{| class="wikitable"
! Date !! Yang Feng !! Jiyuan Zhang
|-
|}

==Past progress==

[[nlp-progress 2016/11]]

[[nlp-progress 2016/10]]

[[nlp-progress 2016/09]]

[[nlp-progress 2016/08]]

[[nlp-progress 2016/05/01 -- 08/16 | nlp-progress 2016/05-07]]

[[nlp-progress 2016/04]]

NLP Status Report 2016-12-05

2016-12-05T05:38:16Z

Guli：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="5"|2016/12/05
|Yang Feng ||
*[[rnng+MN:]] got the result of k-means method and the result is slightly worse;
*fixed the bug;
*analyzed the memory units and changed the calculation of similarity and reran.
*[[S2S+MN:]] read the code and discuss with andy about the implementation details;
*checked Wikianswers data and found the answers are usually much longer than the question;
*read 12 QA-related papers in proceedings of ACL16 and EMNLP16 and haven't found proper dataset yet.
*[[Huilan's work:]] got a version of better result focusing on syntactical transformation.
||
*[[rnng+MN:]] get the result with new similarity calculation.
*[[S2S+MN:]] revise the code of tensorflow to make it equivalent to theano's.
*[[poetry:]] review the code of Jiyuan
*[[Huilan's work:]] continue the work of adding syntactic information.
|-
|Jiyuan Zhang ||
*restructured code
*found the cause of cost randomness
*modified memory weight,ran expriment [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c9/Yanqing-weight%282.0%29.pdf 言情风格][http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/e4/Biansaishi-weight%282.0%29.pdf 边塞风格]
*read a paper
*simply expain my code to Miss Feng
*discussed with liantian about the way of using tensorflow to realize his idea
||
*improve poem model
|-
|Andi Zhang ||
*deal with zh2en data set and ran them on NTM
*had a small breakthrough about the code

||
*get output of encoder to form memory
*continue on the coding work of seq2seq with MemN2N
|-
|Shiyue Zhang ||
* found a bug in my code and modified it.
* tried memory with gate and found a big problem of memory.
* reran previous models, the results are not better than baseline. [[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]]
* reran the original model setting same seed, and got exactly same result.
* published a TRP [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Publication-trp]
||
* try to solve the problem of mem
|-
|Guli ||
* preparing more data set
* working on add translate module to code
* writing a survey about Chinese-uyghur MT
||
* prepare more data
* prepare for Thesis Report
|}

NLP Status Report 2016-12-05

2016-12-05T05:37:17Z

Guli：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="5"|2016/12/05
|Yang Feng ||
*[[rnng+MN:]] got the result of k-means method and the result is slightly worse;
*fixed the bug;
*analyzed the memory units and changed the calculation of similarity and reran.
*[[S2S+MN:]] read the code and discuss with andy about the implementation details;
*checked Wikianswers data and found the answers are usually much longer than the question;
*read 12 QA-related papers in proceedings of ACL16 and EMNLP16 and haven't found proper dataset yet.
*[[Huilan's work:]] got a version of better result focusing on syntactical transformation.
||
*[[rnng+MN:]] get the result with new similarity calculation.
*[[S2S+MN:]] revise the code of tensorflow to make it equivalent to theano's.
*[[poetry:]] review the code of Jiyuan
*[[Huilan's work:]] continue the work of adding syntactic information.
|-
|Jiyuan Zhang ||
*restructured code
*found the cause of cost randomness
*modified memory weight,ran expriment [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c9/Yanqing-weight%282.0%29.pdf 言情风格][http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/e4/Biansaishi-weight%282.0%29.pdf 边塞风格]
*read a paper
*simply expain my code to Miss Feng
*discussed with liantian about the way of using tensorflow to realize his idea
||
*improve poem model
|-
|Andi Zhang ||
*deal with zh2en data set and ran them on NTM
*had a small breakthrough about the code

||
*get output of encoder to form memory
*continue on the coding work of seq2seq with MemN2N
|-
|Shiyue Zhang ||
* found a bug in my code and modified it.
* tried memory with gate and found a big problem of memory.
* reran previous models, the results are not better than baseline. [[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]]
* reran the original model setting same seed, and got exactly same result.
* published a TRP [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Publication-trp]
||
* try to solve the problem of mem
|-
|Guli ||
* writing a survey about Chinese-uyghur MT
* preparing more data set
* working on add translate module to code

||
* prepare more data
* prepare for Thesis Report
|}

Cslt-member-visitors

2016-12-04T06:42:36Z

Guli：/* Li Gu (古丽) */

==Professionals==

===Maoning Wang (王卯宁）===
[[文件:Daisy.jpg|200px]]
* Centeral Fiance and Economic University
* 2016.9-
* Finance processing

===Caixia Wang (王彩霞）===
[[文件:Daisy.jpg|200px]]
* University of diplomatic
* 2016.9-
* Finance processing

=== Yang Feng (冯洋) ===
[[文件:Fengyang.jpg| 200px]]
* 2016.6.21-
* Huilan Ltd
* language processing

==Engineers==

=== Yuxin Zhang (张雨心） ===
[[文件:Daisy.jpg|200px]]
* Haixia research center
* 2016.10 -
* Finance processing

==Students==

===Jiyuan Zhang (张记袁）===
[[文件:Zhangjiyuan.png|200px]]
* PKU
* 2016.4-
* neural generation model
* [[媒体文件:xxx|Bi-weekly report]]
* [[媒体文件:Zhangjy_data.jpg|Data_security_agreement]]

===Jingyi Lin(林婧伊)===
[[文件:JinyiLin_photo.jpg|200px]]
* China chemical university
* 2016.4.12-
* Speech processing
* [[媒体文件:Bi_weekly_report_linjy.ppt|Bi-weekly report]]

===Ziwei Bai (白子薇）===
[[文件:Ziwei Bai.jpg|200px]]
* BUPT
* 2016.5-
* QA
* [[媒体文件:xxx|Bi-weekly report]]

===Ying Shi (石颖）===
[[文件:Ying_shi.jpg|200px]]
* BJTU
* 2016.6.15-
* Speech processing
* [[媒体文件:Shiying_bi_weekly_report.ppt|Bi-weekly report]]

===Aodong Li (李傲冬）===
[[文件:李傲冬.jpg|200px]]
* BUPT
* 2016.6-
* Neural generation model
* [[媒体文件:Biweekly_report_aodong.pptx|Bi-weekly report]]

===Yixiang Chen (陈怿翔)===
[[文件:Chenyx.jpg|200px]]
*University of China Mining
* 2016.7-
* Speech processing
* [[媒体文件:Chenyx_report.pdf |Bi-weekly report]]
* [[媒体文件:Chenyx data.jpg|Data_security_agreement]]

===Shiyue Zhang(张诗悦)===
[[文件:Zhang Shiyue.jpg|200px]]
* BUTP
* 2016.9.06-
* Language processing
* [[媒体文件:xxx|Bi-weekly report]]

===Andy Zhang(张安迪)===
[[文件:andyzhang.jpg|200px]]
* BUPT
* 2016.07.19-
* Language processing
* [[媒体文件:AndyZhang汇报.pptx|Bi-weekly report]]

===Hang Luo (罗航)===
[[文件:罗航.png|200px]]
* PKU
* 2016.10-
* Speech processing
* [[媒体文件:Bi-weekly_work_report_Luohang.pptx|Bi-weekly report]]

===Bin Fu (符宾）===
[[文件:Fubin.jpg|200px]]
* Dalian Haishi
* 2016.10-
* Speech processing

===Li Gu (古丽)===
[[文件:guli.jpg|200px]]
* Xingjiang U.
* 2016.11-
* Translation
*[[媒体文件:3.jpg|Data_security_agreement]]

===Yanqing Wang（王延清）===
[[文件:wyq photo.jpeg|200px]]
* BUPT
* 2016.11-
* Signal processing
* [[媒体文件:Bi-weekly_report.pptx|Bi-weekly report]]
*[[媒体文件:DataSecurityAgreement wangyanqing.jpg|Data_security_agreement]]

===Peilun Xiao（肖培伦）===
[[文件:Daisy.jpg|200px]]
* BUPT
* 2016.12-
* NLP
* [[媒体文件:xxx|Bi-weekly report]]

==Intern==

=== Yang Wei (魏扬） ===
[[文件:weiy_photo.jpg|200px]]
* 2016.10 -
* Speech processing

文件:Guli.jpg

2016-12-04T06:38:49Z

Guli：

文件:3.jpg

2016-12-04T06:35:25Z

Guli：Guli上传“文件:3.jpg”的新版本

Schedule

2016-12-03T05:59:22Z

Guli：/* Daily Report */

Schedule

2016-12-02T02:02:31Z

Guli：/* Daily Report */

Schedule

2016-12-01T09:40:36Z

Guli：/* Daily Report */

NLP Status Report 2016-11-28

2016-11-28T04:33:52Z

Guli：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="5"|2016/11/28
|Yang Feng ||
||
|-
|Jiyuan Zhang ||
||
|-
|Andi Zhang ||
||
|-
|Shiyue Zhang ||
* found a bug in my code and modified it.
* tried memory with gate and found a big problem of memory.
* reran previous models, the results are not better than baseline.
* reran the original model setting same seed, and got exactly same result.
* published a TRP [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Publication-trp]
||
* try to solve the problem of mem
|-
|Guli ||
* busy on nothing for the first two days of the week.
* modify the code and run NMT on fr-en data set
* modify the code and run NMT on ch-uy data set
* writing a survey about Chinese-uyghur MT
||
|}

NLP Status Report 2016-11-21

2016-11-21T01:38:04Z

Guli：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="5"|2016/11/21
|Yang Feng ||
*rnng+mn
1) ran experiments of rnng+mn [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f8/Progress_of_RNNG_with_memory_network.pdf report]] ;
2) used top-k for memory, under training
*sequence-to-sequence + mn
1) wrote the proposal
2) discussed the details with Andy
*intern interview
*Huilan's work
||
*rnng+mn
1) get the result of top-k; 2) try bigger memory;
*sequence-to-sequence + mn
1)coding work
*Huilan's work
1) try syntax-based TM
|-
|Jiyuan Zhang ||
*ran decoder-memory model, but the effect is not obvious
*changed binding way of memory and atten models, can generate different style of poetry
*cleanned up my code
*wrote a techreport about poemGen [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c5/Atten-memory-poetry.pdf]
*submitted two databases about poemGen and musicGen
||
*explored a variety of binding ways of memory and atten model
|-
|Andi Zhang ||
*prepare new data set for paraphrase, wiped out repetition & most of the noises
*run NMT on fr-en data set and new paraphrase set
*read through source code to find ways to modify it
*helped Guli with running NMT on our server
||
*decide to drop theano or not
*start to work on codes
|-
|Shiyue Zhang ||
* run rnng on MKL successfully, which can double or triple the speed.
* rerun the original model and get the final result 92.32
* rerun the wrong memory models, still running
* implement the dynamic memory model and get the result 92.54 which is 0.22 better than baseline
* try another structure of memory [[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]]
||
* try more different models and summary the results
* publish the technical reports
|-
|Guli ||
* read the paper "NMT by jointly learning to align and translate"
* read the codes of paper and ran NMT (cs-en) on GPU with the help of Andi
* learn more about python
* prepare data for Ontology Library
||
* continue to prepare the data
* follow the teacher Yang's instructions
|}