“Nlp-progress 2016/08”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
Andy Zhang
Daily Report
 
(3位用户的8个中间修订版本未显示)
第1行: 第1行:
 +
==Work Progress==
 +
===Daily Report===
 +
 +
{|class="wikitable"
 +
! Date !! Person  !! start!! leave !! hours ||status
 +
|-
 +
| rowspan="4"|2016/08/16 
 +
|Ziwei Bai|| 9:30 || 17:30  || 7 ||learn kernel construction,write the first construction method.
 +
|-
 +
|Andy Zhang||9:30  || 17:30  || 7 || prepare for the ML book, watch Wang's video of neural network
 +
|-
 +
|Aiting Liu|| 9:30  || 17:30  || 7 || learn Wang's instructional video of Neural Network
 +
|-
 +
|Shiyao Li ||  ||  ||  ||
 +
|-
 +
| rowspan="4"|2016/08/17
 +
|Ziwei Bai|| 9:00 || 18:00  || 8 || rewrite 'the property of Gram matrix' and write the second kernel construction method
 +
|-
 +
|Andy Zhang|| 9:00 || 18:00  || 8 || read materials about Radio basis function networks as well as self-organizing map
 +
|-
 +
|Aiting Liu|| 9:00 || 18:00  || 8 || view the information related to the Hopfield network and Boltzmann machine
 +
|-
 +
|Shiyao Li ||  ||  ||  ||
 +
|-
 +
| rowspan="4"|2016/08/18
 +
|Ziwei Bai|| 9:30 ||18:30 || 8 ||learn the 'propert of kernel function'&learn chaos' chatting model predict program
 +
|-
 +
|Andy Zhang||9:30  || 18:30 || 8  || continue preparing for the MLbook
 +
|-
 +
|Aiting Liu||9:30  || 18:30  || 8 || prepare for the presentation, learn RBF
 +
|-
 +
|Shiyao Li ||  ||  ||  ||
 +
|-
 +
| rowspan="4"|2016/08/19
 +
|Ziwei Bai|| 9:00  || 18:00  || 8 || finish the first edition of my work of ML book
 +
|-
 +
|Andy Zhang|| 9:00  || 18:00  || 8 ||learn Hopfield network, prepare for the writing
 +
|-
 +
|Aiting Liu||  9:00 || 18:00  || 8 || learn Andrew Ng's online course
 +
|-
 +
|Shiyao Li ||  ||  ||  ||
 +
|-
 +
| rowspan="4"|2016/08/20
 +
|Ziwei Bai|| 9:40  || 18:50  || 8 || perfect my work of the book
 +
|-
 +
|Andy Zhang||  ||  ||  ||
 +
|-
 +
|Aiting Liu||  ||  ||  ||
 +
|-
 +
|Shiyao Li ||  ||  ||  ||
 +
|-
 +
| rowspan="4"|2016/08/22
 +
|Ziwei Bai|| 9:15  || 18:15 ||8 || test Chatting model ,retrain word vector
 +
|-
 +
|Andy Zhang|| 9:15  || 18:15  || 8 || start writing chapter 3, version 0.0.
 +
|-
 +
|Aiting Liu||  ||  ||  ||
 +
|-
 +
|Shiyao Li ||  ||  ||  ||
 +
|-
 +
| rowspan="4"|2016/08/23
 +
|Ziwei Bai|| 9:00 || 18:15||8 || 1、retrain NRM model & word vec 2.review paper‘NRM for STC’
 +
|-
 +
|Andy Zhang||9:00 || 18:15 || 8 || continue writing the ML book. mainly worked on MLP today
 +
|-
 +
|Aiting Liu||  ||  ||  ||
 +
|-
 +
|Shiyao Li || 9:00  ||  18:15 || 8 || read the book Deep Learning and prepare the presentation of Probability Theory
 +
|-
 +
| rowspan="4"|2016/08/24
 +
|Ziwei Bai|| 9:05 || 18:05 || 8 || test Chatting model 0-8,modify ASR Python Server Functional Specification
 +
|-
 +
|Andy Zhang|| 9:05|| 18:05 ||8 || mainly wrote the section of MLP & RBF
 +
|-
 +
|Aiting Liu||  ||  ||  ||
 +
|-
 +
|Shiyao Li || 9:05  || 18:05 || 8 || finish the preparation of the presentation about Linear Algebra and Probability Theory
 +
|-
 +
| rowspan="4"|2016/08/25
 +
|Ziwei Bai|| 9:20  ||  21:00 || 7.5 || 1、test Chatting Model 9-14,and upload to cvss。2、learn  Bengio‘s dialogue system by hierarchical NN(except experiment and result)。
 +
|-
 +
|Andy Zhang|| 9:20  || 21:00  || 7.5 || continue writing chapter3
 +
|-
 +
|Aiting Liu||  ||  ||  ||
 +
|-
 +
|Shiyao Li || 9:20  ||  21:00 || 7.5 || revise the PPT and start to learn tensorflow
 +
|-
 +
| rowspan="4"|2016/08/26
 +
|Ziwei Bai|| 9:30  ||  18:30 || 8 || prepare for seminar,select 100  posts Suitable for dialogue from weibo data
 +
|-
 +
|Andy Zhang|| 9:30  || 18:30  || 8 || continue writing chapter3
 +
|-
 +
|Aiting Liu||  ||  ||  ||
 +
|-
 +
|Shiyao Li || 9:30  ||  18:30 || 8 || self-study tensorflow
 +
|-
 +
| rowspan="4"|2016/08/27
 +
|Ziwei Bai|| 9:30 || 20:30  || 10 || 1、filter the movie scipts data based on weibo data word vector (30W+pairs) and try to train Chatting Model with the dataset  on the basis of model 31, but load model failed(maybe because the version of tensor flow not consistent).2、find the response Corresponding to the post selected yesterday and test the model (0-34) with it
 +
|-
 +
|Andy Zhang||  ||  ||  ||
 +
|-
 +
|Aiting Liu||  ||  ||  ||
 +
|-
 +
|Shiyao Li||  ||  ||  ||
 +
|-
 +
| rowspan="5"|2016/08/29
 +
|Ziwei Bai|| 9:20 || 18:00  || 7+ || test the Chatting model,count the number of startswith <END> sentences,and natural sentences.
 +
|-
 +
|Andy Zhang|| 9:20  || 17:40  || 7+ || continued working on chapter 3, did some revise work & tried to find ways to draw figures
 +
|-
 +
|Aiting Liu|| 9:20 || 18:20  || 8 || prepare diagrams in the book
 +
|-
 +
|Shiyao Li|| 9:20 || 18:20  || 8 || learn the CNN to solve MNIST using tensorflow
 +
|-
 +
|Aodong Li|| 10:30 || 16:30  || 5 || Read shared paper at the week before the last week
 +
|-
 +
| rowspan="4"|2016/08/30
 +
|Ziwei Bai|| 9:15 ||18:15  || 8 || 1、prepare for bimonthly report.2、test Chatting Model
 +
|-
 +
|Andy Zhang|| 9:15  || 18:15  || 8 || finished version 1 of chapter 3 with the help of Aiting
 +
|-
 +
|Aiting Liu|| 9:15  || 18:15  || 8 || assist Andy to complete chapter3, prepare bimonthly report
 +
|-
 +
|Shiyao Li|| 9:15 || 18:15 || 8 || continue to learn tensorflow and train several models about mnist task
 +
|-
 +
| rowspan="5"|2016/08/31
 +
|Ziwei Bai||9:10 ||  18:10 || 8 || continue to test the Chatting Model
 +
|-
 +
|Andy Zhang|| 9:10  || 18:10  ||8 || continue to modify chapter 3; gave the bimonthly report
 +
|-
 +
|Aiting Liu|| 9:10 || 18:10 || 8 || bimonthly report
 +
|-
 +
|Shiyao Li|| 9:10 || 18:10 || 8 || keep learning word embedding in tensorflow
 +
|-
 +
|Aodong Li|| 08:20 ||  ||  ||
 +
|-
 +
|}
 +
 +
===Month Summary===
 +
 +
{| class="wikitable"
 +
!People!! Summary
 +
|-
 +
|Yang Feng ||
 +
*surveyed the line works of neural parsing, neural Turing machine and variants of RBMs and fixed the research topic to jointly parsing and understanding with Turing machine
 +
*learned tensorflow
 +
*produced two versions of results of query paraphrase
 +
|-
 +
|Jiyuan Zhang ||
 +
*Chinese Song Iambics generaJon with Tensorflow
 +
1. Can produce results with small difference with QiXin’s system
 +
2. Under fine-tuning
 +
*shared a paper and an overview of LSTM、GRU、RBM
 +
|-
 +
|Aodong Li ||
 +
*Code:
 +
  2. Rare word embedding on word2vec and the related in C
 +
  3. Help Lantian for ICASSP
 +
*Paper share: one for bilingual word embedding
 +
*ML book: first version of chapter 2 with Aiting
 +
|-
 +
|Ziwei Bai ||
 +
*finish part of chapter 5 kernel method
 +
*retrain & test Chatting Model
 +
*share 'the use of tensorflow'
 +
|-
 +
|Andy Zhang ||
 +
*shared the principle of word2vec
 +
*read several papers about comparison of sentence similarity
 +
*wrote chapter 3 neural network of the ML book
 +
|-
 +
|Aiting Liu ||
 +
*share two papers:
 +
1.Intrinsic Subspace Evaluation of Word Embedding Representations    [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/6/68/Intrinsic_Subspace_Evaluation_of_Word_Embedding_Representations.pdf pdf]]
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/17/Intrinsic_Subspace_Evaluation_of_Word_Embedding_Representations.pptx slides]]
 +
 +
2.A Sentence Interaction Network for Modeling Dependence between Sentences
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/04/A_Sentence_Interaction_Network_for_Modeling_Dependence_between_Sentences.pdf pdf]]
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/6/6c/A_Sentence_Interaction_Network_for_Modeling_Dependence_between_Sentences.pptx slides]]
 +
*write chapter2 linear model
 +
*help Andy complete chapter3 neural network
 +
|-
 +
|Shiyao Li ||
 +
*prepare the data for question-pair task.
 +
*use SRILM to train the language model and Moses to train the task
 +
*share a paper about LSTM and do a presentation.
 +
|}
 +
 +
===Time Off Table===
 +
 +
{| class="wikitable"
 +
! Date !! Yang Feng !! Jiyuan Zhang !! Aodong Li !! Ziwei Bai !! Andy Zhang !! Aiitng Liu !! Shiyao Li
 +
|-
 +
|2016/8/15 || || || || || || || 8 hours
 +
|-
 +
|2016/8/16 || || || || || || || 8 hours
 +
|-
 +
|2016/8/17 || || || || || || || 8 hours
 +
|-
 +
|2016/8/18 || 2 hours || || || || || || 4 hours
 +
|-
 +
|2016/8/19 || || 6 hours || || || || || 8 hours
 +
|-
 +
|2016/8/22 || || || || || || 8 hours || 8 hours
 +
|-
 +
|2016/8/23 || || 2 hours || || || || 8 hours ||
 +
|-
 +
|2016/8/24 || || || || || || 8 hours ||
 +
|-
 +
|2016/8/25 || || || || || || 8 hours ||
 +
|-
 +
|2016/8/26 || || || 5 hours || || || 8 hours ||
 +
|-
 +
|2016/8/29 || || || 0.5 hours || || || ||
 +
|}
 +
 +
 
=Aiting Liu=
 
=Aiting Liu=
 
2016-08-15 ~ 2016-08-16 :  learn Neural Network  
 
2016-08-15 ~ 2016-08-16 :  learn Neural Network  
第40行: 第257行:
  
 
==Shiyao Li==
 
==Shiyao Li==
 +
 +
 +
 +
==Ziwei Bai==
 +
2016-08-08 ~2016-08-10:
 +
            prepare for slide for tensorflow
 +
2016-08-11 ~2016-08-12:
 +
            write the first edition of 'dual representation' & 'Gram matrix'
 +
2016-08-15:
 +
            find parper about chatting model published in 2016

2016年9月10日 (六) 02:21的最后版本

Work Progress

Daily Report

Date Person start leave hours status
2016/08/16 Ziwei Bai 9:30 17:30 7 learn kernel construction,write the first construction method.
Andy Zhang 9:30 17:30 7 prepare for the ML book, watch Wang's video of neural network
Aiting Liu 9:30 17:30 7 learn Wang's instructional video of Neural Network
Shiyao Li
2016/08/17 Ziwei Bai 9:00 18:00 8 rewrite 'the property of Gram matrix' and write the second kernel construction method
Andy Zhang 9:00 18:00 8 read materials about Radio basis function networks as well as self-organizing map
Aiting Liu 9:00 18:00 8 view the information related to the Hopfield network and Boltzmann machine
Shiyao Li
2016/08/18 Ziwei Bai 9:30 18:30 8 learn the 'propert of kernel function'&learn chaos' chatting model predict program
Andy Zhang 9:30 18:30 8 continue preparing for the MLbook
Aiting Liu 9:30 18:30 8 prepare for the presentation, learn RBF
Shiyao Li
2016/08/19 Ziwei Bai 9:00 18:00 8 finish the first edition of my work of ML book
Andy Zhang 9:00 18:00 8 learn Hopfield network, prepare for the writing
Aiting Liu 9:00 18:00 8 learn Andrew Ng's online course
Shiyao Li
2016/08/20 Ziwei Bai 9:40 18:50 8 perfect my work of the book
Andy Zhang
Aiting Liu
Shiyao Li
2016/08/22 Ziwei Bai 9:15 18:15 8 test Chatting model ,retrain word vector
Andy Zhang 9:15 18:15 8 start writing chapter 3, version 0.0.
Aiting Liu
Shiyao Li
2016/08/23 Ziwei Bai 9:00 18:15 8 1、retrain NRM model & word vec 2.review paper‘NRM for STC’
Andy Zhang 9:00 18:15 8 continue writing the ML book. mainly worked on MLP today
Aiting Liu
Shiyao Li 9:00 18:15 8 read the book Deep Learning and prepare the presentation of Probability Theory
2016/08/24 Ziwei Bai 9:05 18:05 8 test Chatting model 0-8,modify ASR Python Server Functional Specification
Andy Zhang 9:05 18:05 8 mainly wrote the section of MLP & RBF
Aiting Liu
Shiyao Li 9:05 18:05 8 finish the preparation of the presentation about Linear Algebra and Probability Theory
2016/08/25 Ziwei Bai 9:20 21:00 7.5 1、test Chatting Model 9-14,and upload to cvss。2、learn Bengio‘s dialogue system by hierarchical NN(except experiment and result)。
Andy Zhang 9:20 21:00 7.5 continue writing chapter3
Aiting Liu
Shiyao Li 9:20 21:00 7.5 revise the PPT and start to learn tensorflow
2016/08/26 Ziwei Bai 9:30 18:30 8 prepare for seminar,select 100 posts Suitable for dialogue from weibo data
Andy Zhang 9:30 18:30 8 continue writing chapter3
Aiting Liu
Shiyao Li 9:30 18:30 8 self-study tensorflow
2016/08/27 Ziwei Bai 9:30 20:30 10 1、filter the movie scipts data based on weibo data word vector (30W+pairs) and try to train Chatting Model with the dataset on the basis of model 31, but load model failed(maybe because the version of tensor flow not consistent).2、find the response Corresponding to the post selected yesterday and test the model (0-34) with it
Andy Zhang
Aiting Liu
Shiyao Li
2016/08/29 Ziwei Bai 9:20 18:00 7+ test the Chatting model,count the number of startswith <END> sentences,and natural sentences.
Andy Zhang 9:20 17:40 7+ continued working on chapter 3, did some revise work & tried to find ways to draw figures
Aiting Liu 9:20 18:20 8 prepare diagrams in the book
Shiyao Li 9:20 18:20 8 learn the CNN to solve MNIST using tensorflow
Aodong Li 10:30 16:30 5 Read shared paper at the week before the last week
2016/08/30 Ziwei Bai 9:15 18:15 8 1、prepare for bimonthly report.2、test Chatting Model
Andy Zhang 9:15 18:15 8 finished version 1 of chapter 3 with the help of Aiting
Aiting Liu 9:15 18:15 8 assist Andy to complete chapter3, prepare bimonthly report
Shiyao Li 9:15 18:15 8 continue to learn tensorflow and train several models about mnist task
2016/08/31 Ziwei Bai 9:10 18:10 8 continue to test the Chatting Model
Andy Zhang 9:10 18:10 8 continue to modify chapter 3; gave the bimonthly report
Aiting Liu 9:10 18:10 8 bimonthly report
Shiyao Li 9:10 18:10 8 keep learning word embedding in tensorflow
Aodong Li 08:20

Month Summary

People Summary
Yang Feng
  • surveyed the line works of neural parsing, neural Turing machine and variants of RBMs and fixed the research topic to jointly parsing and understanding with Turing machine
  • learned tensorflow
  • produced two versions of results of query paraphrase
Jiyuan Zhang
  • Chinese Song Iambics generaJon with Tensorflow
1. Can produce results with small difference with QiXin’s system
2. Under fine-tuning
  • shared a paper and an overview of LSTM、GRU、RBM
Aodong Li
  • Code:
 2. Rare word embedding on word2vec and the related in C
 3. Help Lantian for ICASSP
  • Paper share: one for bilingual word embedding
  • ML book: first version of chapter 2 with Aiting
Ziwei Bai
  • finish part of chapter 5 kernel method
  • retrain & test Chatting Model
  • share 'the use of tensorflow'
Andy Zhang
  • shared the principle of word2vec
  • read several papers about comparison of sentence similarity
  • wrote chapter 3 neural network of the ML book
Aiting Liu
  • share two papers:

1.Intrinsic Subspace Evaluation of Word Embedding Representations [pdf] [slides]

2.A Sentence Interaction Network for Modeling Dependence between Sentences [pdf] [slides]

  • write chapter2 linear model
  • help Andy complete chapter3 neural network
Shiyao Li
  • prepare the data for question-pair task.
  • use SRILM to train the language model and Moses to train the task
  • share a paper about LSTM and do a presentation.

Time Off Table

Date Yang Feng Jiyuan Zhang Aodong Li Ziwei Bai Andy Zhang Aiitng Liu Shiyao Li
2016/8/15 8 hours
2016/8/16 8 hours
2016/8/17 8 hours
2016/8/18 2 hours 4 hours
2016/8/19 6 hours 8 hours
2016/8/22 8 hours 8 hours
2016/8/23 2 hours 8 hours
2016/8/24 8 hours
2016/8/25 8 hours
2016/8/26 5 hours 8 hours
2016/8/29 0.5 hours


Aiting Liu

2016-08-15 ~ 2016-08-16 : learn Neural Network

2016-08-08 ~ 2016-08-12 :

   1.finish the first version of chapter2
   2.read paper "A Sentence Interaction Network for Modeling Dependence between Sentences"    [pdf]


2016-08-05: write section probabilistic PCA

2016-08-04: write section softmax regression

2016-08-03: write section logistic regression

2016-08-02: write section polynomial fitting and linear regression

2016-08-01: learn linear model , determine the content of the chapter2


Andy Zhang

2016-08-15:

           prepare for the writing of the ML book, watched video and read some materials

2016-08-05:

           Give a report on my research on sentence similarity

2016-08-04:

           Give a representation on NNLMs; review papers read earlier this week.

2016-08-03:

           Read the paper Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks

2016-08-02:

           Read the paper Modeling Interestingness with Deep Neural Networks

2016-08-01:

           Read papers about ABCNN for modeling sentence pairs


Shiyao Li

Ziwei Bai

2016-08-08 ~2016-08-10:

           prepare for slide for tensorflow

2016-08-11 ~2016-08-12:

           write the first edition of 'dual representation' & 'Gram matrix'

2016-08-15:

           find parper about chatting model published in 2016