Schedule

来自cslt Wiki
2016年5月9日 (一) 03:16Xingchao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)
  • Aodong Li (李傲冬)
  • Ziwei Bai (白子薇)
  • Aiting Liu (刘艾婷)

Work Process

Question answering system


Chao Xing

2016-05-09 :

            Day Plan : 
                1. Test CDSSM model in chatting model.
                2. Read paper : 
                   Learning from Real Users Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems
                   SimpleDS A Simple Deep Reinforcement Learning Dialogue System
                3. Code RNN by myself in tensorflow.

2016-05-08 :

            Fix some problem in dialogue system team, and continue read some papers in dialogue system.

2016-05-07 :

            Read some papers in dialogue system.

2016-05-06 :

            Try to fix RNN-DSSM model in tensorflow. Failure..

2016-05-05 :

            Coding for RNN-DSSM in tensorflow. Face an error when running rnn-dssm model in cpu : memory keep increasing. 
            Tensorflow's version in huilan is 0.7.0 and install by pip, this cause using error in creating gpu graph,
            one possible solution is build tensorflow from source code.

Aiting Liu


2016-05-08:Fetch data from 'http://news.ifeng.com/' and 'http://www.xinhuanet.com/'(13.4M)

2016-05-07:Fetch data from 'http://fangtan.china.com.cn/' and interview books (10M)

2016-05-04:Establish the overall framework of our chat robot,and continue to build database

Ziwei Bai


2016-05-08: convert the pdf we found yesterday into txt,and reconstruct the data into our expected formula

2016-05-07: Finding 9 Drama scripts and 20 film scripts

2016-05-04:Finding and dealing with the data for QA system

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


2016-04-22
  • Speed up process of the test performance about theano version of Generationg the similar questions' vectors based on RNN.

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)

2016-04-28 : Given a talk to text team for some recently paper.
              Knowledge Base Completion via Search-Based Question Answering : pdf
              Open Domain Question Answering via Semantic Enrichment  : pdf
              A Neural Conversational Model : pdf
              And given a tiny results for CNN-DSSM in huilan's weekly report.
2016-04-27 : Code Multi-layer CNN, suffered from memory error in GPU in tensorflow.
              So I run such test on CPU, should slow.
2016-04-26 : Code done tricky & analysis such tricky.
2016-04-25 : Find a tricky to improve accuracy given by Tianyi.
            : Code for this tricky.
2016-04-23 : Set a series of experiment set.
              1. Try deep CNN-DSSM, current model just follow proposed model contain one convolution layer, need to be a tuneable parameter.
              2. Test whether mixture data effective to current model and deep CDSSM.
              3. Code Recurrent CNN-DSSM (new approach.)
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 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
2016-4-25~29:replace rnnrbm with lstmrbm, then run lstmrbm's model

Question & Answering (Aiting Liu)

2016-04-24 : make my biweekly report
2016-04-23 : read Fader's paper (2011)
2016-04-20 : read Fader's paper (2013)
2016-04-15 : learn dssm and sent2vec
2016-04-16 : try to figure out how the PARALAX dataset is constructed
2016-04-17 : download the PARALAX dataset and try to turn it into what we want it to be

Generation Model (Aodong li)

2016-05-08 :
   denoise and train word vectors of  Lijun Deng's lyrics (110+ pieces)
   decide on using raw sequence to sequence model
2016-05-07 :
   study attention-based model
   learn some details about the poem generation model
   change my focus onto lyrics generation model
2016-05-06 : read the paper about poem generation and learn about LSTM
2016-05-05 : check in and have an overview of generation model