gmftbyGMFTBY/MultiTurnDialogZoo

Issues

• 使用中文数据集

  #16 opened 2 years ago by Banana-lwz
  0

• 关于ubuntu数据集，seq2seqNoAttention效果太好

  #15 opened 3 years ago by Mrwangkedong
  0

• data/data_process 文件夹里貌似没有Ubuntu corpus的预处理脚本？

  #7 opened 4 years ago by ZihaoW123
  1

• _

  #13 opened 3 years ago by isxychao
  0

• _

  #14 opened 3 years ago by isxychao
  0

• RuntimeError: The size of tensor a (31) must match the size of tensor b (30) at non-singleton dimension 0

  #12 opened 4 years ago by 27182812
  1

• When can models stop training?

  #9 opened 4 years ago by ZihaoW123
  4

• output = output[:, :, :self.hidden_size] + output[:, :, self.hidden_size:]，why？

  #11 opened 4 years ago by Asymptote0902
  1

• The performances when using ReCoSa

  #10 opened 4 years ago by devjwsong
  2

• Performance on DailyDialog dataset

  #8 opened 4 years ago by aman229
  1

• Which one is the best one?

  #6 opened 5 years ago by timsoraro
  5

• The dataset only have 3 file instead 6 file.

  #5 opened 5 years ago by liyuan97
  4

• The result of Seq2Seq

  #4 opened 5 years ago by JBoRu
  4

• training epochs

  #3 opened 5 years ago by katherinelyx
  10

• An inquiry about ReCoSa model

  #2 opened 5 years ago by sonyawong
  3

• baseline models

  #1 opened 5 years ago by marvinzh
  29