NLP Status Report 2017-6-5

From cslt Wiki
Revision as of 05:56, 5 June 2017 by Zhangsy (Talk | contribs)

Jump to: navigation, search
Date People Last Week This Week
2017/6/5 Jiyuan Zhang
Aodong LI
  • Small data:
 Only make the English encoder's embedding constant -- 45.98
 Only initialize the English encoder's embedding and then finetune it -- 46.06
 Share the attention mechanism and then directly add them -- 46.20
  • big data baseline bleu = 30.83
  • Model with three fixed embeddings
 Shrink output vocab from 30000 to 20000 and best result is 31.53
 Train the model with 40 batch size and best result until now is 30.63
  • test more checkpoints on model trained with batch = 40
  • train model with reverse output
Shiyue Zhang
  • trained word2vec on big data, and directly used it on NMT, but resulted in quite poor performance
  • trained M-NMT model, got bleu=36.58 (+1.34 than NMT). But found the EOS in mem has a big influence on result:
NMT 35.24, 57.7/39.8/31.9/27.0 BP=0.939
MNMT (EOS=1) 35.27, 60.0/41.3/33.1/28.0 BP=0.907
MNMT (EOS=0.2) 36.40, 59.1/40.8/32.6/27.4 BP=0.951
MNMT (EOS=0) 36.58, 58.4/40.4/32.1/27.0 BP=0.968
Shipan Ren