“NLP Status Report 2017-7-10”版本间的差异

• reproduced the couplet model using moses

• continue to modify the couplet

• Tried seq2seq with or without attention model to do style transfer (cross domain) task but this didn't work due to overfitting

 seq2seq with attention model: Chinese-to-English
 vanilla seq2seq model: English-to-English (Unsupervised)

• Read two style controlled papers in generative model field
• Trained seq2seq with style code model

• Understand the model and mechanism mentioned in the two related papers
• Figure out new ways to do style transfer task

• read and run ViVi_NMT code
• read the API of tensorflow
• debugged ViVi_NMT and upgraded code version to tensorflow1.0
• found the new version saves more time，has lower complexity and better bleu than before

• test two versions of the code on small data sets (Chinese-English) and large data sets (Chinese-English) respectively
• test two versions of the code on WMT 2014 English-to-German parallel dataset and WMT 2014 English-French dataset respectively
• record experimental results
• read paper and try to make the bleu become a little better