A research project for natural language generation, containing the official implementations by MSRA NLC team.
686
stars
109
forks
source link
What's the difference between using bi-gram directly and the proposed loss function? #18
Open
nickcom007 opened 4 years ago
When n=2, why not use bi-gram directly for the loss? It will save a lot of computation cost. What is the difference if all weights αn = 0?