Does String-Based Neural MT Learn Source Syntax?

Xing Shi1, Inkit Padhi1, Kevin Knight2
1University of Southern California, 2USC/ISI


Abstract

We investigate whether a neural, encoder-decoder translation system learns syntactic information on the source side as a by-product of training. We propose two methods to detect whether the encoder has learned local and global source syntax. A fine-grained analysis of the syntactic structure learned by the encoder reveals which kinds of syntax are learned and which are missing.