cslt Wiki - 用户贡献 [zh-cn]

NLP Status Report 2017-4-5

2017-04-05T02:16:12Z

Fengyang：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/4/5
|Yang Feng ||
* Got the sampled 100w good data and ran Moses (BLEU: 30.6)
* Reimplemented the idea of ACL (added some optimization to the previous code) and check the performance in the following gradual steps: 1. use s_i-1 as memory query; 2. use s_i-1+c_i as memory query; 3. use y as the memory states for attention; 4. use y + smt_attentions * h as memory states for attention.
* ran experiments for the above steps but the loss was inf. I am looking for reasons.
||
*do experiments and write the paper
|-
|Jiyuan Zhang ||
* I did keyword expansion on the qx's model
*fixed some bugs
*read two papers
||
*improve the effect of the qx's model
|-
|Andi Zhang ||
*revise the original oov model so that it can automatically detect oov words and translate them
*deal with the situation that source word is oov but target word is not oov first
*it didn't predict right
||
*make the model work as what we wanted
*deal with the situation that source word is oov and target word is also oov, then other situations
|-
|Shiyue Zhang ||
* got a reasonable baseline on big zhen data
||
* implement mem model on this baseline, and test on big data
|-
|Peilun Xiao ||

||

|}

NLP Status Report 2017-4-5

2017-04-05T02:15:21Z

Fengyang：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/4/5
|Yang Feng ||
* Got the sampled 100w good data and ran Moses (BLEU: 30.6)
* Reimplemented the idea of ACL (added some optimization to the previous code) and check the performance in the following gradual steps: 1. use s\_i-1 as memory query; 2. use s\_i-1+c\_i as memory query; 3. use y as the memory states for attention; 4. use y + smt_attentions * h as memory states for attention.
* ran experiments for the above steps but the loss was inf. I am looking for reasons.
||
*do experiments and write the paper
|-
|Jiyuan Zhang ||
* I did keyword expansion on the qx's model
*fixed some bugs
*read two papers
||
*improve the effect of the qx's model
|-
|Andi Zhang ||
*revise the original oov model so that it can automatically detect oov words and translate them
*deal with the situation that source word is oov but target word is not oov first
*it didn't predict right
||
*make the model work as what we wanted
*deal with the situation that source word is oov and target word is also oov, then other situations
|-
|Shiyue Zhang ||
* got a reasonable baseline on big zhen data
||
* implement mem model on this baseline, and test on big data
|-
|Peilun Xiao ||

||

|}

NLP Status Report 2017-4-5

2017-04-05T02:14:59Z

Fengyang：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/4/5
|Yang Feng ||
* Got the sampled 100w good data and ran Moses (BLEU: 30.6)
* Reimplemented the idea of ACL (added some optimization to the previous code) and check the performance in the following gradual steps: 1. use s\_i-1 as memory query; 2. use s\_i-1+c\_i
as memory query; 3. use y as the memory states for attention; 4. use y + smt_attentions * h as memory states for attention.
* ran experiments for the above steps but the loss was inf. I am looking for reasons.
||
*do experiments and write the paper
|-
|Jiyuan Zhang ||
* I did keyword expansion on the qx's model
*fixed some bugs
*read two papers
||
*improve the effect of the qx's model
|-
|Andi Zhang ||
*revise the original oov model so that it can automatically detect oov words and translate them
*deal with the situation that source word is oov but target word is not oov first
*it didn't predict right
||
*make the model work as what we wanted
*deal with the situation that source word is oov and target word is also oov, then other situations
|-
|Shiyue Zhang ||
* got a reasonable baseline on big zhen data
||
* implement mem model on this baseline, and test on big data
|-
|Peilun Xiao ||

||

|}

NLP Status Report 2017-4-5

2017-04-05T02:14:30Z

Fengyang：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/4/5
|Yang Feng ||
* Got the sampled 100w good data and ran Moses (BLEU: 30.6)
* Reimplemented the idea of ACL (added some optimization to the previous code) and check the performance in the following gradual steps: 1. use s_i-1 as memory query; 2. use s_i-1+c_i
as memory query; 3. use y as the memory states for attention; 4. use y + smt_attentions * h as memory states for attention.
* ran experiments for the above steps but the loss was inf. I am looking for reasons.
||
*do experiments and write the paper
|-
|Jiyuan Zhang ||
* I did keyword expansion on the qx's model
*fixed some bugs
*read two papers
||
*improve the effect of the qx's model
|-
|Andi Zhang ||
*revise the original oov model so that it can automatically detect oov words and translate them
*deal with the situation that source word is oov but target word is not oov first
*it didn't predict right
||
*make the model work as what we wanted
*deal with the situation that source word is oov and target word is also oov, then other situations
|-
|Shiyue Zhang ||
* got a reasonable baseline on big zhen data
||
* implement mem model on this baseline, and test on big data
|-
|Peilun Xiao ||

||

|}

NLP Status Report 2017-4-5

2017-04-05T01:58:28Z

Fengyang：以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/3/27 |Yang Feng || *tested for the baseline but cannot get the reasonable result...”为内容创建页面

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/3/27
|Yang Feng ||
*tested for the baseline but cannot get the reasonable result.
*debug the baseline to try to reproduce the good result but failed.
*fixed the problem of nan in alpha-gamma method but the result is not good.
*changed the calculation of probability for alpha-gamma method but the result is neither good.
*ran Moses for cwmt zh-en translation, but the training data is case-sensitive, so need to rerun.
||
*rerun Moses for cwmt zh-en and cs-en
*decide to use tensorflow or theano
*run experiments based on the chosen platform
|-
|Jiyuan Zhang ||
* I did nothing (I found my ACL mark was at borderline, so I didn't have a mind to work)
||
*improve the effect of the qx's model
|-
|Andi Zhang ||
*fixed the bug, turns out it rises from the unfamiliarity with numpy.resize() function
*the demo model can deal with oov problem(both source word and target word are oov)
||
*some paper work about graduation design
*run some experiments using theano on old data set and new zh2en from lihang
|-
|Shiyue Zhang ||
* got good results from gnmt
* but haven't found the way to implement our model on gnmt
* trying to modify our code to make it work on big data
||
* go on trying to modify our code to make it work on big data
* go on looking into gnmt code
|-
|Peilun Xiao ||

||

|}

2017-4-5

2017-04-05T01:56:04Z

Fengyang：以“NLP Status Report 2017-4-5 ASR Status Report 2017-4-5 FIN Status Report 2017-4-5 FreeNeb Status Report 2017-4-5”为内容创建页面

[[NLP Status Report 2017-4-5]]

[[ASR Status Report 2017-4-5]]

[[FIN Status Report 2017-4-5]]

[[FreeNeb Status Report 2017-4-5]]

Status report

2017-04-05T01:55:12Z

Fengyang：

[[2017-4-5]]

[[2017-3-27]]

[[2017-3-20]]

[[2017-3-13]]

[[2017-3-6]]

[[2017-2-27]]

[[2017-2-20]]

[[2017-2-13]]

[[2017-2-6]]

[[2017-1-30]]

[[2017-1-23]]

[[2017-1-16]]

[[2017-1-10]]

[[2017-1-3]]

NLP Status Report 2017-3-20

2017-03-27T07:44:22Z

Fengyang：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/3/20
|Yang Feng ||
*went through the code and made different attempt, and managed to produce the good result (47-->50 on the small zh-en data set)
*wrote the cross-entropy method for alpha-gamma method, but found it is different from the built-in method.
*changed to use the build-in soft-cross-entropy method and ran experiments
||
*get the result for alpha-gamma method
*run experiments on the big data
|-
|Jiyuan Zhang ||
||

|-
|Andi Zhang ||

||

|-
|Shiyue Zhang ||

||

|-
|Peilun Xiao ||

||

|}

NLP Status Report 2017-3-20

2017-03-27T07:43:39Z

Fengyang：以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/3/20 |Yang Feng || *went through the code and made different attempt, and manage...”为内容创建页面

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/3/20
|Yang Feng ||
*went through the code and made different attempt, and managed to produce the good result
*wrote the cross-entropy method for alpha-gamma method, but found it is different from the built-in method.
*changed to use the build-in soft-cross-entropy method and ran experiments
||
*get the result for alpha-gamma method
*run experiments on the big data
|-
|Jiyuan Zhang ||
||

|-
|Andi Zhang ||

||

|-
|Shiyue Zhang ||

||

|-
|Peilun Xiao ||

||

|}

NLP Status Report 2017-3-27

2017-03-27T07:30:12Z

2017-3-27

2017-03-27T06:16:59Z

Fengyang：以“NLP Status Report 2017-3-27 ASR Status Report 2017-3-27 FIN Status Report 2017-3-27 FreeNeb Status Report 2017-3-27”为内容创建页面

[[NLP Status Report 2017-3-27]]

[[ASR Status Report 2017-3-27]]

[[FIN Status Report 2017-3-27]]

[[FreeNeb Status Report 2017-3-27]]

Status report

2017-03-27T06:14:46Z

Fengyang：

[[2017-3-27]]

[[2017-3-20]]

[[2017-3-13]]

[[2017-3-6]]

[[2017-2-27]]

[[2017-2-20]]

[[2017-2-13]]

[[2017-2-6]]

[[2017-1-30]]

[[2017-1-23]]

[[2017-1-16]]

[[2017-1-10]]

[[2017-1-3]]

文件:Nmt mn report continue.pdf

2017-03-13T05:52:14Z

Fengyang：Fengyang上传“文件:Nmt mn report continue.pdf”的新版本

NLP Status Report 2017-3-13

2017-03-13T05:50:00Z

Fengyang：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
* tested and analyzed the results on the cs-en data set (30.4 on the heldout-training set and 7.3 on the dev set);
* added masks to the baseline (44.4 on the cn-en);
* added encoder-masks and memory-masks to alpha-gamma method and fixed the bugs. Got an improvement of 0.5 again the masked baseline [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/b8/Nmt_mn_report_continue.pdf report]];
* To avoid doing softmax twice, rewrite the softmax_cross_entropy function myself. (under-training)
||
* analyze and improve the alpha-gamma method.
|-
|Jiyuan Zhang ||

||
|-
|Andi Zhang ||

||

|-
|Shiyue Zhang ||

||

|-
|Peilun Xiao ||

||

|}

NLP Status Report 2017-3-13

2017-03-13T05:33:06Z

Fengyang：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
* tested and analyzed the results on the cs-en data set (30.4 on the heldout-training set and 7.3 on the dev set);
* added masks to the baseline (44.4 on the cn-en);
* added masks to alpha-gamma method and fixed the bugs. Got an improvement of 0.5 again the masked baseline [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/b8/Nmt_mn_report_continue.pdf report]];
* To avoid doing softmax twice, rewrite the softmax_cross_entropy function myself. (under-training)
||
* analyze and improve the alpha-gamma method.
|-
|Jiyuan Zhang ||

||
|-
|Andi Zhang ||

||

|-
|Shiyue Zhang ||

||

|-
|Peilun Xiao ||

||

|}

文件:Nmt mn report continue.pdf

2017-03-13T05:32:24Z

Fengyang：

NLP Status Report 2017-3-13

2017-03-13T05:26:58Z

Fengyang：以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/1/3 |Yang Feng || * ran experiments on the CS-EN data set (200k pairs) with tota...”为内容创建页面

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
* ran experiments on the CS-EN data set (200k pairs) with totally identical initialization as the paper. on the sampled 2k training sentences, the bleu is 19.5 (not converged yet). (the bleu on the test set expected to be 26)
* add the alpha and gamma score and do multi-task training. Without multi-task training, the loss didn't decline on the training data, but with multi-task training, the loss did decline.
* prepared for Huilan's inspection.
||
* Analyze the reason that the loss didn't decline with alpha and gamma
* test for multi-task training;
* improve the baseline for the CS-EN
|-
|Jiyuan Zhang ||
* reproduced planning neural network [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/38/Planning_neural_network_initial_decode.pdf results]
||
*reproduce planning neural network
|-
|Andi Zhang ||
* added source masks in attention_decoder where calculates attention and in gru_cell where calculates new states.
* found the attribute sentence_length, perhaps it works better than my code
||

|-
|Shiyue Zhang ||
* figured out the problem of attention: the initial value of V should be around 0
* tested different modification, such as add mask, init b with 0.
* Compared the results, and concluded only change the initial value of V is the best.
||
* try to get right attention on memory
|-
|Peilun Xiao ||

||

|}

2017-3-13

2017-03-13T05:26:26Z

Fengyang：以“NLP Status Report 2017-3-13 ASR Status Report 2017-3-13 FIN Status Report 2017-3-13 FreeNeb Status Report 2017-3-13”为内容创建页面

[[NLP Status Report 2017-3-13]]

[[ASR Status Report 2017-3-13]]

[[FIN Status Report 2017-3-13]]

[[FreeNeb Status Report 2017-3-13]]

Status report

2017-03-13T04:38:26Z

Fengyang：

[[2017-3-13]]

[[2017-3-6]]

[[2017-2-27]]

[[2017-2-20]]

[[2017-2-13]]

[[2017-2-6]]

[[2017-1-30]]

[[2017-1-23]]

[[2017-1-16]]

[[2017-1-10]]

[[2017-1-3]]

2017-3-6

2017-03-06T10:56:11Z

Fengyang：

NLP Status Report 2017-1-23

2017-03-02T10:42:08Z

Fengyang：以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/1/3 |Yang Feng || * prepare for ACL || *prepare for ACL |- |Jiyuan Zhang || ||...”为内容创建页面

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
* prepare for ACL
||
*prepare for ACL
|-
|Jiyuan Zhang ||

||

|-
|Andi Zhang ||

||

|-
|Shiyue Zhang ||

||

|-
|Peilun Xiao ||

||

|}

NLP Status Report 2017-2-6

2017-03-02T10:41:12Z

NLP Status Report 2017-1-30

2017-03-02T10:41:02Z

2017-2-6

2017-03-02T10:39:59Z

Fengyang：以“NLP Status Report 2017-2-6 ASR Status Report 2017-2-6 FIN Status Report 2017-2-6 FreeNeb Status Report 2017-2-6”为内容创建页面

[[NLP Status Report 2017-2-6]]

[[ASR Status Report 2017-2-6]]

[[FIN Status Report 2017-2-6]]

[[FreeNeb Status Report 2017-2-6]]

2017-1-30

2017-03-02T10:39:31Z

Fengyang：以“NLP Status Report 2017-1-30 ASR Status Report 2017-1-30 FIN Status Report 2017-1-30 FreeNeb Status Report 2017-1-30”为内容创建页面

[[NLP Status Report 2017-1-30]]

[[ASR Status Report 2017-1-30]]

[[FIN Status Report 2017-1-30]]

[[FreeNeb Status Report 2017-1-30]]

2017-1-23

2017-03-02T10:38:59Z

Fengyang：以“NLP Status Report 2017-1-23 ASR Status Report 2017-1-23 FIN Status Report 2017-1-23 FreeNeb Status Report 2017-1-23”为内容创建页面

[[NLP Status Report 2017-1-23]]

[[ASR Status Report 2017-1-23]]

[[FIN Status Report 2017-1-23]]

[[FreeNeb Status Report 2017-1-23]]

Status report

2017-03-02T10:38:01Z

Fengyang：

[[2017-2-27]]

[[2017-2-20]]

[[2017-2-13]]

[[2017-2-6]]

[[2017-1-30]]

[[2017-1-23]]

[[2017-1-16]]

[[2017-1-10]]

[[2017-1-3]]

NLP Status Report 2017-2-27

2017-03-02T10:36:40Z

Fengyang：以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/1/3 |Yang Feng || * ran baseline with different parameters * Huilan's work || *...”为内容创建页面

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
* ran baseline with different parameters
* Huilan's work
||
* Huilan's work
* run experiments for memory networks
|-
|Jiyuan Zhang ||

||

|-
|Andi Zhang ||

||

|-
|Shiyue Zhang ||

||

|-
|Peilun Xiao ||

||

|}

NLP Status Report 2017-2-20

2017-03-02T10:24:54Z

Fengyang：以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/1/3 |Yang Feng || * prepare for IJCAI. || * improve baseline. |- |Jiyuan Zhang |...”为内容创建页面

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
* prepare for IJCAI.
||
* improve baseline.
|-
|Jiyuan Zhang ||

||

|-
|Andi Zhang ||

||

|-
|Shiyue Zhang ||

||

|-
|Peilun Xiao ||

||

|}

NLP Status Report 2017-2-13

2017-03-02T10:22:42Z

Fengyang：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
* prepare for ACL and IJCAI.
||
*prepare for IJCAI
|-
|Jiyuan Zhang ||

||

|-
|Andi Zhang ||

||

|-
|Shiyue Zhang ||

||

|-
|Peilun Xiao ||

||

|}

NLP Status Report 2017-2-13

2017-03-02T10:17:06Z

Fengyang：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
* prepare for ACL and IJCAI.
||
*prepare for IJCAI
|-
|Jiyuan Zhang ||
*assisted wangyang to build the questionnaire's website
*completed the questionnaire
||
*complete the evalation
*start to wirte paper
|-
|Andi Zhang ||

||

|-
|Shiyue Zhang ||
* finished implementing beam search on tensorflow seq2seq translation model
||
* add BLUE part to validate the function of beam search
* go on with Dynet Chinese Document
|-
|Peilun Xiao ||

||

|}

NLP Status Report 2017-2-13

2017-03-02T10:15:48Z

Fengyang：以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/1/3 |Yang Feng || * nmt+mn: ran experiments with only 3-entry memory to chec...”为内容创建页面

Status check list

2017-03-02T09:11:06Z

Fengyang：/* Current status */

==Rules for scoring==

===Score symbol===
:*-: pass;
:*X: no input;
:*X-:delayed pass;
:*=: not clear;
:*'#': bad performance;
:*O: expected absence
:*+: excellent input and nice progress, with clear deliver(paper, TRP, patent, system, code..).

===Member symbol===
:*PV: Part-time Visitor: daily report on nlp.cslt.org or asr.cslt.org
:*PVE: Part-time Engineering: report your supervisor
:*FV: Full-time Visitor : weekly report
:*SV: Special Visitor : weekly report
:*E: Engineer : weekly report
:*S: Student : weekly report
:*I: Student Intern: daily report

===Principle for PLUS(+)===

#TRP, put on http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Publication-trp
#Paper submission, put in the form of TRP (above link) and arxiv
#Data collection, put on /nfs/coprpus0, and indexed on wiki
#code and document delivery, put on gitlab.cslt.org
#patent, put on http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Publication-patents
#model, put on the archive disk, sent delivery email, and put the model in the release sheet on wiki.
#help others with extra much effort
#'''Leaders' pluses are from their group members'''

===Publication guide===

*http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/ASR-publication_process

==Current status==
{| class="wikitable"
! !! ASR !! !! !! !! !! !! !!!!Finance !! !! !! !!!! NLP !! !! !!
|-
! !!TangZY !! LiLT !! ShiYing!! ChenYX !! LuoH !! LinJY !! WangYQ !!!! WangY !! Yuxin!!WangYD !! RenTZ !!!! FengY !! ZhangJY!! ZhangSY !! Andy Zhang
|-
!Deadline || S || S || FV || PV || PV || PV || PV |||| S || SV || PV || PV |||| SV || FV || PV || PV
|-
|2017-2-6 || O || O || O || O || O || O || O |||| O || O || O || O |||| O || O || 2 ||
|-
|2017-2-13|| - || - || - || 0 || 0 || 0 || 0 |||| - || 0 || - || - |||| 0+m || 0+p || 4+m || +pm
|-
|2017-2-20|| - || - || 0 || 0 || 0 || 0 || 0 |||| - || - || - || - |||| || || 6 ||
|-
|2017-2-27|| - || - || - || - || - || 0 || 0 |||| - || - || - || - |||| || || 2 ||
|-
|}

* p : poetry generation with memory networks
* m : memory- augmented neural machine translation

==January==

{| class="wikitable"
! !! ASR !! !! !! !! !! !! !!!!Finance !! !! !! !!!! NLP !! !!
|-
! !!TangZY !! LiLT !! ShiYing!! ChenYX !! LuoH !! LinJY !! WangYQ !!!! WangY !! Yuxin!!WangYD !! RenTZ !!!! FengY !! ZhangJY!! ZhangSY
|-
!Deadline || S || S || FV || PV || PV || PV || PV |||| S || SV || I || I |||| SV || FV || PV
|-
|2017-1-9|| - || - || - 3 || - 3 || - 3 || X 4.5 || X(a) |||| - || - || - || - |||| - || - || 0.5
|-
|2017-1-16|| - || - || - || O || O 4 || O 2 || O |||| - || - || - || - |||| - || - || 3
|-
|2017-1-23|| O || O || O || O || O || O || O |||| 0 || 0 || 0 || 0 |||| 0 || 0 || 0
|-
|2017-1-30|| O || O || O || O || O || O || O |||| 0 || 0 || 0 || 0 |||| 0 || 0 || 0
|-
|}

* a: code and doc for "Driver's Distraction Detection"[https://github.com/CSLT-THU/Demo-for-Driver-s-Distraction-Detection]

[[Template]]

{| class="wikitable"
! !! ASR !! !! !! !! !! !! !!!!Finance !! !! !! !!!! NLP !! !! !! !! !!
|-
! !!TangZY !! LiLT !! ShiYing!! ChenYX !! LuoH !! LinJY !! WangYQ !!!! WangY !! Yuxin!!WangYD !! RenTZ !!!! FengY !! ZhangJY!! ZhangSY!! LiAD !! Andy !! Guli
|-
!Deadline || S || S || PV || PV || PV || PV || PV |||| S || SV || I || I |||| SV || FV || PV || PV || PV || PV
|-
|2016-12-05|| - || - || - 3.5 || - 4 || - || 0 || - 1.5 |||| - || - || || |||| +d || +d || 2- || || 3- || 3-
|-
|2016-12-12|| +(c) || +(c) || - 6 || +(c) 6 || - || 0 || - |||| - || - || || |||| +g || - || 3- || || 4- || 5-
|-
|2016-12-19|| - || - || - 4 || - 3 || - 1 || - 1 || - |||| - || - || - || - |||| +e || - || 3.5+e || || 5- || 5-
|-
|2016-12-26|| +(abi) || +(a) || +(b)9.5||+(a)2.5 || +(i) 6 || - 6.5 || - 1 |||| +h || - || + || - |||| - || - || 6- || || 6.5- || 7-
|-
|}

* a: TRP-20160012 "基于Kaldi i-vector的说话人识别系统使用说明"
* b: TRP-20160015 How to run ASR system for Kazak (in Chinese)
* c: TRP-20160011 on Replay detection
* d: poem generation
* e: rnng+mn
* f: nmt+mn
* g: Moses manual
* h: factordb
* i: TRP-20160016 How to deploy joint training in Kaldi (in Chinese)

==Former status check==

===[[asr-status-check-archive-2016|2016]]===

===[[asr-status-check-archive-2015|2015]]===

===[[asr-status-check-archive-2014|2014]]===

===[[asr-status-check-archive-2013|2013]]===

Status check list

2017-03-02T09:10:33Z

Fengyang：/* Current status */

==Rules for scoring==

===Score symbol===
:*-: pass;
:*X: no input;
:*X-:delayed pass;
:*=: not clear;
:*'#': bad performance;
:*O: expected absence
:*+: excellent input and nice progress, with clear deliver(paper, TRP, patent, system, code..).

===Member symbol===
:*PV: Part-time Visitor: daily report on nlp.cslt.org or asr.cslt.org
:*PVE: Part-time Engineering: report your supervisor
:*FV: Full-time Visitor : weekly report
:*SV: Special Visitor : weekly report
:*E: Engineer : weekly report
:*S: Student : weekly report
:*I: Student Intern: daily report

===Principle for PLUS(+)===

#TRP, put on http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Publication-trp
#Paper submission, put in the form of TRP (above link) and arxiv
#Data collection, put on /nfs/coprpus0, and indexed on wiki
#code and document delivery, put on gitlab.cslt.org
#patent, put on http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Publication-patents
#model, put on the archive disk, sent delivery email, and put the model in the release sheet on wiki.
#help others with extra much effort
#'''Leaders' pluses are from their group members'''

===Publication guide===

*http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/ASR-publication_process

==Current status==
{| class="wikitable"
! !! ASR !! !! !! !! !! !! !!!!Finance !! !! !! !!!! NLP !! !! !!
|-
! !!TangZY !! LiLT !! ShiYing!! ChenYX !! LuoH !! LinJY !! WangYQ !!!! WangY !! Yuxin!!WangYD !! RenTZ !!!! FengY !! ZhangJY!! ZhangSY !! Andy Zhang
|-
!Deadline || S || S || FV || PV || PV || PV || PV |||| S || SV || PV || PV |||| SV || FV || PV || PV
|-
|2017-2-6 || O || O || O || O || O || O || O |||| O || O || O || O |||| O || O || 2 ||
|-
|2017-2-13|| - || - || - || 0 || 0 || 0 || 0 |||| - || 0 || - || - |||| 0+m || 0+p || 4+m ||
|-
|2017-2-20|| - || - || 0 || 0 || 0 || 0 || 0 |||| - || - || - || - |||| || || 6 ||
|-
|2017-2-27|| - || - || - || - || - || 0 || 0 |||| - || - || - || - |||| || || 2 ||
|-
|}

* p : poetry generation with memory networks
* m : memory- augmented neural machine translation

==January==

{| class="wikitable"
! !! ASR !! !! !! !! !! !! !!!!Finance !! !! !! !!!! NLP !! !!
|-
! !!TangZY !! LiLT !! ShiYing!! ChenYX !! LuoH !! LinJY !! WangYQ !!!! WangY !! Yuxin!!WangYD !! RenTZ !!!! FengY !! ZhangJY!! ZhangSY
|-
!Deadline || S || S || FV || PV || PV || PV || PV |||| S || SV || I || I |||| SV || FV || PV
|-
|2017-1-9|| - || - || - 3 || - 3 || - 3 || X 4.5 || X(a) |||| - || - || - || - |||| - || - || 0.5
|-
|2017-1-16|| - || - || - || O || O 4 || O 2 || O |||| - || - || - || - |||| - || - || 3
|-
|2017-1-23|| O || O || O || O || O || O || O |||| 0 || 0 || 0 || 0 |||| 0 || 0 || 0
|-
|2017-1-30|| O || O || O || O || O || O || O |||| 0 || 0 || 0 || 0 |||| 0 || 0 || 0
|-
|}

* a: code and doc for "Driver's Distraction Detection"[https://github.com/CSLT-THU/Demo-for-Driver-s-Distraction-Detection]

[[Template]]

{| class="wikitable"
! !! ASR !! !! !! !! !! !! !!!!Finance !! !! !! !!!! NLP !! !! !! !! !!
|-
! !!TangZY !! LiLT !! ShiYing!! ChenYX !! LuoH !! LinJY !! WangYQ !!!! WangY !! Yuxin!!WangYD !! RenTZ !!!! FengY !! ZhangJY!! ZhangSY!! LiAD !! Andy !! Guli
|-
!Deadline || S || S || PV || PV || PV || PV || PV |||| S || SV || I || I |||| SV || FV || PV || PV || PV || PV
|-
|2016-12-05|| - || - || - 3.5 || - 4 || - || 0 || - 1.5 |||| - || - || || |||| +d || +d || 2- || || 3- || 3-
|-
|2016-12-12|| +(c) || +(c) || - 6 || +(c) 6 || - || 0 || - |||| - || - || || |||| +g || - || 3- || || 4- || 5-
|-
|2016-12-19|| - || - || - 4 || - 3 || - 1 || - 1 || - |||| - || - || - || - |||| +e || - || 3.5+e || || 5- || 5-
|-
|2016-12-26|| +(abi) || +(a) || +(b)9.5||+(a)2.5 || +(i) 6 || - 6.5 || - 1 |||| +h || - || + || - |||| - || - || 6- || || 6.5- || 7-
|-
|}

* a: TRP-20160012 "基于Kaldi i-vector的说话人识别系统使用说明"
* b: TRP-20160015 How to run ASR system for Kazak (in Chinese)
* c: TRP-20160011 on Replay detection
* d: poem generation
* e: rnng+mn
* f: nmt+mn
* g: Moses manual
* h: factordb
* i: TRP-20160016 How to deploy joint training in Kaldi (in Chinese)

==Former status check==

===[[asr-status-check-archive-2016|2016]]===

===[[asr-status-check-archive-2015|2015]]===

===[[asr-status-check-archive-2014|2014]]===

===[[asr-status-check-archive-2013|2013]]===

Status check list

2017-03-02T09:07:38Z

Fengyang：/* Current status */

==Rules for scoring==

===Score symbol===
:*-: pass;
:*X: no input;
:*X-:delayed pass;
:*=: not clear;
:*'#': bad performance;
:*O: expected absence
:*+: excellent input and nice progress, with clear deliver(paper, TRP, patent, system, code..).

===Member symbol===
:*PV: Part-time Visitor: daily report on nlp.cslt.org or asr.cslt.org
:*PVE: Part-time Engineering: report your supervisor
:*FV: Full-time Visitor : weekly report
:*SV: Special Visitor : weekly report
:*E: Engineer : weekly report
:*S: Student : weekly report
:*I: Student Intern: daily report

===Principle for PLUS(+)===

#TRP, put on http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Publication-trp
#Paper submission, put in the form of TRP (above link) and arxiv
#Data collection, put on /nfs/coprpus0, and indexed on wiki
#code and document delivery, put on gitlab.cslt.org
#patent, put on http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Publication-patents
#model, put on the archive disk, sent delivery email, and put the model in the release sheet on wiki.
#help others with extra much effort
#'''Leaders' pluses are from their group members'''

===Publication guide===

*http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/ASR-publication_process

==Current status==
{| class="wikitable"
! !! ASR !! !! !! !! !! !! !!!!Finance !! !! !! !!!! NLP !! !! !!
|-
! !!TangZY !! LiLT !! ShiYing!! ChenYX !! LuoH !! LinJY !! WangYQ !!!! WangY !! Yuxin!!WangYD !! RenTZ !!!! FengY !! ZhangJY!! ZhangSY !! Andy Zhang
|-
!Deadline || S || S || FV || PV || PV || PV || PV |||| S || SV || PV || PV |||| SV || FV || PV || PV
|-
|2017-2-6 || O || O || O || O || O || O || O |||| O || O || O || O |||| O || O || 2 ||
|-
|2017-2-13|| - || - || - || 0 || 0 || 0 || 0 |||| - || 0 || - || - |||| 0+m || 0+p || 4+m ||
|-
|2017-2-20|| - || - || 0 || 0 || 0 || 0 || 0 |||| - || - || - || - |||| || || 6 ||
|-
|2017-2-27|| - || - || - || - || - || 0 || 0 |||| - || - || - || - |||| || || 2 ||
|-
|}

==January==

{| class="wikitable"
! !! ASR !! !! !! !! !! !! !!!!Finance !! !! !! !!!! NLP !! !!
|-
! !!TangZY !! LiLT !! ShiYing!! ChenYX !! LuoH !! LinJY !! WangYQ !!!! WangY !! Yuxin!!WangYD !! RenTZ !!!! FengY !! ZhangJY!! ZhangSY
|-
!Deadline || S || S || FV || PV || PV || PV || PV |||| S || SV || I || I |||| SV || FV || PV
|-
|2017-1-9|| - || - || - 3 || - 3 || - 3 || X 4.5 || X(a) |||| - || - || - || - |||| - || - || 0.5
|-
|2017-1-16|| - || - || - || O || O 4 || O 2 || O |||| - || - || - || - |||| - || - || 3
|-
|2017-1-23|| O || O || O || O || O || O || O |||| 0 || 0 || 0 || 0 |||| 0 || 0 || 0
|-
|2017-1-30|| O || O || O || O || O || O || O |||| 0 || 0 || 0 || 0 |||| 0 || 0 || 0
|-
|}

* a: code and doc for "Driver's Distraction Detection"[https://github.com/CSLT-THU/Demo-for-Driver-s-Distraction-Detection]

[[Template]]

{| class="wikitable"
! !! ASR !! !! !! !! !! !! !!!!Finance !! !! !! !!!! NLP !! !! !! !! !!
|-
! !!TangZY !! LiLT !! ShiYing!! ChenYX !! LuoH !! LinJY !! WangYQ !!!! WangY !! Yuxin!!WangYD !! RenTZ !!!! FengY !! ZhangJY!! ZhangSY!! LiAD !! Andy !! Guli
|-
!Deadline || S || S || PV || PV || PV || PV || PV |||| S || SV || I || I |||| SV || FV || PV || PV || PV || PV
|-
|2016-12-05|| - || - || - 3.5 || - 4 || - || 0 || - 1.5 |||| - || - || || |||| +d || +d || 2- || || 3- || 3-
|-
|2016-12-12|| +(c) || +(c) || - 6 || +(c) 6 || - || 0 || - |||| - || - || || |||| +g || - || 3- || || 4- || 5-
|-
|2016-12-19|| - || - || - 4 || - 3 || - 1 || - 1 || - |||| - || - || - || - |||| +e || - || 3.5+e || || 5- || 5-
|-
|2016-12-26|| +(abi) || +(a) || +(b)9.5||+(a)2.5 || +(i) 6 || - 6.5 || - 1 |||| +h || - || + || - |||| - || - || 6- || || 6.5- || 7-
|-
|}

* a: TRP-20160012 "基于Kaldi i-vector的说话人识别系统使用说明"
* b: TRP-20160015 How to run ASR system for Kazak (in Chinese)
* c: TRP-20160011 on Replay detection
* d: poem generation
* e: rnng+mn
* f: nmt+mn
* g: Moses manual
* h: factordb
* i: TRP-20160016 How to deploy joint training in Kaldi (in Chinese)

==Former status check==

===[[asr-status-check-archive-2016|2016]]===

===[[asr-status-check-archive-2015|2015]]===

===[[asr-status-check-archive-2014|2014]]===

===[[asr-status-check-archive-2013|2013]]===

NLP Status Report 2017-1-16

2017-01-16T04:57:00Z

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
* [[nmt+mn:]] ran experiments with only 3-entry memory to check the impact of memory;
* check the translations and also ran experiments to analyze the results [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/07/Nmt_mn_result_summary.xlsx translation]] [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Nmt_mn_report.pdf report]];
* add c_i and y_i-1 to improve the fluency;
* fix a bug of baseline of using different embedding for forward and backward rnns (under-running);
||
*[[nmt+mn:]] do more experiments
|-
|Jiyuan Zhang ||
*assisted wangyang to build the questionnaire's website
*completed the questionnaire
||
*complete the evalation
*start to wirte paper
|-
|Andi Zhang ||

||

|-
|Shiyue Zhang ||
* finished running theano baseline
* read and understood the beam search in theano baseline
* started to write the [http://dynet-doc-zh.readthedocs.io/zh_CN/latest/ Dynet Chinese Document]
* started to implement beam search to tensorflow baseline
||
* finished the beam search implementation
* go on with Dynet Chinese Document
|-
|Peilun Xiao ||

||

|}

2017-1-16

2017-01-16T04:56:40Z

Fengyang：

[[NLP Status Report 2017-1-16]]

[[ASR Status Report 2017-1-16]]

[[FIN Status Report 2017-1-16]]

[[FreeNeb Status Report 2017-1-16]]

NLP Status Report 2017-1-10

2017-01-16T04:51:14Z

Fengyang：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
*[[nmt+mn:]] fixed the problem of generating unreasonable results of baselines;
* ran experiments [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Nmt_mn_report.pdf report]];
* polished and submitted the TRP of Moses;
* wrote the code of result analysis (under-going);
||
*[[nmt+mn:]] analyze results;
*do more experiments
|-
|Jiyuan Zhang ||
*designed the questionnaire, then discovered some problems and redesigned
||
*complete the questionnaire
|-
|Andi Zhang ||
*helped Jiyuan dealing with poem questionnaires
||
*continue this work, may start collecting feedback if all questionnaires are filled out
|-
|Shiyue Zhang ||
* finished running theano baseline
* read and understood the beam search in theano baseline
* started to write the [http://dynet-doc-zh.readthedocs.io/zh_CN/latest/ Dynet Chinese Document]
* started to implement beam search to tensorflow baseline
||
* finished the beam search implementation
* go on with Dynet Chinese Document
|-
|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
|}

2017-1-16

2017-01-16T04:50:43Z

Fengyang：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
* [[nmt+mn:]] ran experiments with only 3-entry memory to check the impact of memory;
* check the translations and also ran experiments to analyze the results [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/07/Nmt_mn_result_summary.xlsx translation]] [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Nmt_mn_report.pdf report]];
* add c_i and y_i-1 to improve the fluency;
* fix a bug of baseline of using different embedding for forward and backward rnns (under-running);
||
*[[nmt+mn:]] do more experiments
|-
|Jiyuan Zhang ||
*designed the questionnaire, then discovered some problems and redesigned
||
*complete the questionnaire
|-
|Andi Zhang ||

||

|-
|Shiyue Zhang ||
* finished running theano baseline
* read and understood the beam search in theano baseline
* started to write the [http://dynet-doc-zh.readthedocs.io/zh_CN/latest/ Dynet Chinese Document]
* started to implement beam search to tensorflow baseline
||
* finished the beam search implementation
* go on with Dynet Chinese Document
|-
|Peilun Xiao ||

||

|}

NLP Status Report 2017-1-10

2017-01-16T04:49:04Z

Fengyang：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
* [[nmt+mn:]] ran experiments with only 3-entry memory to check the impact of memory;
* check the translations and also ran experiments to analyze the results [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/07/Nmt_mn_result_summary.xlsx translation]] [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Nmt_mn_report.pdf report]];
* add c_i and y_i-1 to improve the fluency;
* fix a bug of baseline of using different embedding for forward and backward rnns (under-running);
||
*[[nmt+mn:]] *do more experiments
|-
|Jiyuan Zhang ||
*designed the questionnaire, then discovered some problems and redesigned
||
*complete the questionnaire
|-
|Andi Zhang ||
*helped Jiyuan dealing with poem questionnaires
||
*continue this work, may start collecting feedback if all questionnaires are filled out
|-
|Shiyue Zhang ||
* finished running theano baseline
* read and understood the beam search in theano baseline
* started to write the [http://dynet-doc-zh.readthedocs.io/zh_CN/latest/ Dynet Chinese Document]
* started to implement beam search to tensorflow baseline
||
* finished the beam search implementation
* go on with Dynet Chinese Document
|-
|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
|}

文件:Nmt mn result summary.xlsx

2017-01-16T04:48:43Z

Fengyang：Fengyang上传“文件:Nmt mn result summary.xlsx”的新版本

文件:Nmt mn report.pdf

2017-01-16T04:47:59Z

Fengyang：Fengyang上传“文件:Nmt mn report.pdf”的新版本

2017-1-16

2017-01-16T04:36:46Z

Fengyang：以“{| class="wikitable" !Date !! People !! Last Week !! This Week |- | rowspan="6"|2017/1/3 |Yang Feng || *nmt+mn: fixed the problem of generating unreasonable resu...”为内容创建页面

Status report

2017-01-16T04:35:43Z

Fengyang：

[[2017-1-16]]

[[2017-1-10]]

[[2017-1-3]]

文件:Nmt mn report.pdf

2017-01-13T07:57:38Z

Fengyang：Fengyang上传“文件:Nmt mn report.pdf”的新版本

文件:Nmt mn result summary.xlsx

2017-01-13T07:53:10Z

Fengyang：

文件:Nmt mn report.pdf

2017-01-10T06:34:51Z

Fengyang：Fengyang上传“文件:Nmt mn report.pdf”的新版本

NLP Status Report 2017-1-10

2017-01-10T06:33:42Z

Fengyang：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
*[[nmt+mn:]] fixed the problem of generating unreasonable results of baselines;
* ran experiments [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Nmt_mn_report.pdf report]];
* polished and submitted the TRP of Moses;
* wrote the code of result analysis (under-going);
||
*[[nmt+mn:]] analyze results;
*use the embedding of word2vec;
*do more experiments
|-
|Jiyuan Zhang ||
*designed the questionnaire, then discovered some problems and redesigned
||
*complete the questionnaire
|-
|Andi Zhang ||
*helped Jiyuan dealing with poem questionnaires
||
*continue this work, may start collecting feedback if all questionnaires are filled out
|-
|Shiyue Zhang ||
* finished running theano baseline
* read and understood the beam search in theano baseline
* started to write the [http://dynet-doc-zh.readthedocs.io/zh_CN/latest/ Dynet Chinese Document]
* started to implement beam search to tensorflow baseline
||
* finished the beam search implementation
* go on with Dynet Chinese Document
|-
|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 2017-1-10

2017-01-10T06:33:22Z

Fengyang：

{| class="wikitable"
!Date !! People !! Last Week !! This Week
|-
| rowspan="6"|2017/1/3
|Yang Feng ||
*[[nmt+mn:]] fix the problem of generating unreasonable results of baselines;
* ran experiments [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Nmt_mn_report.pdf report]];
* polish and submit the TRP of Moses;
* wrote the code of result analysis (under-going);
||
*[[nmt+mn:]] analyze results;
*use the embedding of word2vec;
*do more experiments
|-
|Jiyuan Zhang ||
*designed the questionnaire, then discovered some problems and redesigned
||
*complete the questionnaire
|-
|Andi Zhang ||
*helped Jiyuan dealing with poem questionnaires
||
*continue this work, may start collecting feedback if all questionnaires are filled out
|-
|Shiyue Zhang ||
* finished running theano baseline
* read and understood the beam search in theano baseline
* started to write the [http://dynet-doc-zh.readthedocs.io/zh_CN/latest/ Dynet Chinese Document]
* started to implement beam search to tensorflow baseline
||
* finished the beam search implementation
* go on with Dynet Chinese Document
|-
|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
|}

文件:Nmt mn report.pdf

2017-01-10T06:32:52Z

Fengyang：Fengyang上传“文件:Nmt mn report.pdf”的新版本