Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Unsupervised Dependency Parsing: Let's Use Supervised Parsers

About

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 state-of-the-part parser of Spitkovsky et al. (2013) on the WSJ corpus.

Phong Le, Willem Zuidema• 2015

Related benchmarks

TaskDatasetResultRank
Dependency ParsingWSJ (test)
UAS65.8
67
Dependency ParsingWSJ 10 or fewer words (test)
UAS73.2
25
Unsupervised Dependency ParsingWSJ section 23 (all lengths) (test)
Directed Dependency Accuracy (DDA)65.8
16
Unsupervised Dependency ParsingWSJ section 23 length <= 10 (test)
DDA73.2
16
Dependency ParsingWSJ corpus all sentences (section 23)
DDA66.2
9
Dependency ParsingWSJ corpus length up to 10 (section 23)
DDA73.2
9
Showing 6 of 6 rows

Other info

Follow for update