Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation

Elena Voita
Elena Voita
Cited by: 1|Views4

Abstract:

In Neural Machine Translation (and, more generally, conditional language modeling), the generation of a target token is influenced by two types of context: the source and the prefix of the target sequence. While many attempts to understand the internal workings of NMT models have been made, none of them explicitly evaluates relative sou...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments