Open kweonwooj opened 6 years ago
Do you have the code of this paper?
@chenustc I cannot find the public code released by MS for this paper. I don't have the implementation.
@chenustc If it helps, I'm currently working on an implementation of this paper. Having trouble getting it to good results using what's specified in the paper. I'll message you somehow when things start looking good.
Update: I had stopped earlier due to not matching Microsoft's performance. I might attempt again later.
@Choco31415 If you have implemented this paper, please message me too. Thank you~
@Choco31415 Please message me too, thanks!
@Choco31415 Hi brother,have finished that code? I am in need of the code,would you do me a favor to send it to me? My email: cuihuijun@foxmail.com
https://github.com/ustctf-zz/delibnet I don't know if this would help. As stated in this paper https://aclanthology.org/P19-1653.pdf, they initialize encoder and first-pass decoder with a vanilla seq2seq model, and use this model to generate samples for second-pass decoder. I'm not sure if this is the standard practice in the original Deliberation Network.
Abstract
Details
Deliberation
is a polishing process often seen in human cognitive behaviors during translation, writing and readingDeliberation Network
Training Algorithm
x
, 1st pass decoder generates a sampley'
that 2nd pass decoder learns fromActual Training Implementation
Results
Qualitative Analysis
egypt's middle east
->egypt says the middle east
Future Works
Personal Thoughts
Link : https://papers.nips.cc/paper/6775-deliberation-networks-sequence-generation-beyond-one-pass-decoding.pdf Authors : Xia et al. 2017