Unsupervised Dependency Parsing: Let's Use Supervised Parsers

Phong Le, Willem Zuidema
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
We present a self-training approach to unsupervised dependency parsing that reuses existing supervised and unsupervised parsing algorithms. Our approach, called 'iterated reranking' (IR), starts with dependency trees generated by an unsupervised parser, and iteratively improves these trees using the richer probability models used in supervised parsing that are in turn trained on these trees. Our system achieves 1.8% accuracy higher than the stateof-the-part parser of Spitkovsky et al. (2013) on the WSJ corpus.
doi:10.3115/v1/n15-1067 dblp:conf/naacl/LeZ15 fatcat:4x5fntotm5g2bk6wm6tc3p7nt4