Also known as "unsupervised dependency parsing"
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
The encoder part of our model is discriminative and globally normalized which allows us to use rich features as well as universal linguistic priors.
Inspired by second-order supervised dependency parsing, we proposed a second-order extension of unsupervised neural dependency models that incorporate grandparent-child or sibling information.
Ranked #1 on Dependency Grammar Induction on WSJ10