Parsing Universal Dependencies without training
2017-01-11EACL 2017Code Available0· sign in to hype
Héctor Martínez Alonso, Željko Agić, Barbara Plank, Anders Søgaard
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/hectormartinez/ud_unsup_parserOfficialIn papernone★ 22
Abstract
We propose UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of head attachment rules. It features two-step decoding to guarantee that function words are attached as leaf nodes. The parser requires no training, and it is competitive with a delexicalized transfer system. UDP offers a linguistically sound unsupervised alternative to cross-lingual parsing for UD, which can be used as a baseline for such systems. The parser has very few parameters and is distinctly robust to domain change across languages.