Schedule

来自cslt Wiki
2016年4月23日 (六) 06:23Xingchao讨论 | 贡献的版本

跳转至: 导航搜索

Text Processing Team Schedule

Members

Former Members

  • 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
  • DongXu Zhang (张东旭) : --

Current Members

  • Tianyi Luo (骆天一)
  • Chao Xing (邢超)
  • Qixin Wang (王琪鑫)
  • Yiqiao Pan (潘一桥)

Work Process

Similar questions senetence vector model training with RNN/LSTM and the attention RNN/LSTM chatting model training (Tianyi Luo)


2016-04-21
  • Finish helping Teacher Wang to prepare for text group's presentation(Tang poetry and Songci generation and Intelligent QA system) for Tsinghua University's 105 anniversary.
  • Submit our IJCAI paper to arxiv. (Solve a big problem about submitting the paper including Chinese chacracters. Solution)
  • Optimize theano version of Generationg the similar questions' vectors based on RNN.

2016-04-20
  • Finish submiting the camera version paper of IJCAI 2016.
  • Update the version of Technical Report about Chinese Song Iambics generation.

2016-04-19
  • Optimize theano version of Generationg the similar questions' vectors based on RNN.

2016-04-18
  • Optimize theano version of Generationg the similar questions' vectors based on RNN.
  • Finish implementing theano version of LSTM Max margin vector training.

Reproduce DSSM Baseline (Chao Xing)

2016-04-22 : Find a problem : Use labs' gpu machine 970 iteration per time is 1537 second but huilan's server is just 7 second.
              Achieve reasonable results when apply max-margin method to CNN-DSSM model.
2016-04-21 : True DSSM model doesn't work well, analysis as below:
               1. Not exactly reproduce DSSM model, because the original one is English version, I just adapt it to Chinese but after word segmentation. 
                  So the input is tri-gram words not tri-gram letter.
               2. Our dataset far from rich, because of we do not use pre-trained word vectors as initial vectors, we can hardly achieve good performance.
            : Request
               1. As we have rich pre-trained word vectors, maybe CDSSM or RDSSM corrected to our task.
               2. Different length of sequences seek to be fixed dimension vectors, just CNN and RNN can do such things, DNN can not do it by using 
                 fix length of word vectors
            : Coding done CDSSM. Test for it's performance.
               One problem : When you install tensorflow by pip 0.8.0 and you want to use conv2d function by gpu, you need make sure you had already 
                            install your cudnn's version as 4.0 not lastest 5.0.
2016-04-20 : Find reproduced DSSM model's bug, fix it.
2016-04-19 : Code mixture data model by less memory dependency done. Test it's performance.
2016-04-18 : Code mixture data model.
2016-04-16 : Code mixture data model, but face to memory error. Dr. Wang help me fix it.
2016-04-15 : Share Papers. Investigation a series of DSSM papers for future work. And show our intern students how to do research.
            : Original DSSM model : Learning Deep Structured Semantic Models for Web Search using Clickthrough Data pdf
            : CNN based DSSM model : A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval pdf
            : Use DSSM model for a new area : Modeling Interestingness with Deep Neural Networks pdf
            : Latest approach for LSTM + RNN DSSM model : SEMANTIC MODELLING WITH LONG-SHORT-TERM MEMORY FOR INFORMATION RETRIEVAL pdf
2016-04-14 : Test dssm-dnn model, code dssm-cnn model.
              Continue investigate deep neural question answering system.
2016-04-13 : test dssm model, investigate deep neural question answering system.
            : Share theano ppt theano
            : Share tensorflow ppt tensorflow
2016-04-12 : Write done dssm tensor flow version.
2016-04-11 : Write tensorflow toolkit ppt for intern student.
2016-04-10 : Learn tensorflow toolkit.
2016-04-09 : Learn tensorflow toolkit.
2016-04-08 : Finish theano version.

Deep Poem Processing With Image (Ziwei Bai)

2016-04-20 :combine my program with Qixin Wang's
2016-04-10 : web spider to catch a thousand pices of images.
2016-04-13 :1、download theano for python2.7。 2.debug cnn.py
2016-04-15 :web spider to catch 30 thousands pices of images and store them into a matrix
2016-04-16 :modify the code of CNN and spider
2016-04-17 :train convouloutional neural network

RNN Music Processing for lyric (Shiyao Li)

2016-04-20 : learn LSTM
2016-04-09 : web spider to catch a thousand pieces of lyrics.
2016-04-10 : extract the keywords in the lyrics
2016-04-13 :Read paper Memory Network.
2016-04-15 :read the paper Memory Network and start to understand its code
2016-04-17 :read paper end to end memory network

RNN Key word Poem Processing (Yi Xiong)

2016-04-22 : Code a web spider to recursively catch link of keywords from Baidu
2016-04-09 : Database for N-Gram data storing
2016-04-10 : dictionary stored in database , dictionary based segmentation and a simple bigram segmentation
2016-04-13 : segmentation result analysis
2016-04-15 :improve the simple bigram segmentation
2016-04-16 :compare the result of bigram segmentation with dictionary segmentation
2016-04-17 :learn python (head first 50%)
2016-04-20 : learn web spider

RNN Piano Processing (Jiyuan Zhang)

2016-4-12:select appropriate midis and run rnnrbm model
2016-4-13:view rnnrbm model‘s code
2016-4-14~15:coding to select 4/4 beat of midis
2016-4-17~22:run data, failed several times ,then modify code and view rnnrbm model's code

Recommendation System (Tong Liu)

2016-04-09 : 1.read a review:Machine learning:Trends,perspectives, and prospects 2.learn python ,can operate dict and set
2016-04-12 : 1.read paper Collaborative Deep Learning for Recommender Systems and take notes.2. learn the concepts of stacked denoising autoencoder(SDAE).
2016-04-17 :1.allocate PuTTy and Xming 2.learn python, can operate slice and iterator 3.learn release and datasets of a paper: Collaborative Deep Learning for Recommender Systems

Question & Answering (Aiting Liu)

2016-04-20 : read Fader's paper ()2013
2016-04-15 :learn dssm and sent2vec
2016-04-16 :try to figure out how thePARALAX dataset is constructed
2016-04-17 :download the PARALAX dataset and turn it into what we want it to be