Huilian-cslt-week-2015-12-31

来自cslt Wiki
2015年12月31日 (四) 05:15Zxw讨论 | 贡献的版本

(差异) ←上一版本 | 最后版本 (差异) | 下一版本→ (差异)
跳转至: 导航搜索

Environment

  • buy a 12G DELL K40 server done
  • configure the system done

RNN Poem Processing

  • attention training from Renmin newspaper done --Qixin Wang done
  • change corpus done
  • contact specialists of Song Peams done
  • write a patent done
  • submit a patent --Xinkai(1.15)
  • demo release(unified model) done
  • add to language model information

RNN Writing Processing

  • write code done -- Chao Xing
  • generate Xing style using variational RNN
  • use mnist dataset done
  • train using chinese dataset
  • train reference to the paper of BAYESIAN PROBABILISTIC PROGRAM FOR IMAGE GENERATION

RNN QA

  • rnn rescore
  • rnn rescore should be used as a factor for learning to rank
  • similar question --Bingdong
  • Huilan test -- Tianyi Luo(12.17)
  • train corpus of word vector--hulian
  • add traditional method of learning to rank--Tianyi
  • memory machine(about three months)--Tianyi


Couplet

  • attention training done --Tianyi Luo
  • focused attending training(12.17)
  • revise training corpus(12.17)