Stop-probability estimates computed on a large corpus improve Unsupervised Dependency Parsing
David Marecek and Milan Straka
The 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013)
Sofia, Bulgaria, August 4-9, 2013
Even though the quality of unsupervised dependency parsers grows, they often fail in recognition of very basic dependencies. In this paper, we exploit a prior knowledge of STOP-probabilities (whether a given word has any children in a given direction), which is obtained from a large raw corpus using a reducibility principle. By incorporating this knowledge into Dependency Model with Valence, we managed to considerably outperform the state-of-the-art results in terms of average attachment score over 20 treebanks from CoNLL 2006 and 2007 shared task.
Conference Manager (V2.61.0 - Rev. 2792M)