Paper: LingPars A Linguistically Inspired Language-Independent Machine Learner For Dependency Treebanks

ACL ID W06-2923
Title LingPars A Linguistically Inspired Language-Independent Machine Learner For Dependency Treebanks
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2006
Authors
  • Eckhard Bick (University of Southern Denmark, Odense Denmark)

This paper presents a Constraint Grammar- inspired machine learner and parser, Ling­ Pars, that assigns dependencies to morpho­ logically annotated treebanks in a function- centred way. The system not only bases at­ tachment probabilities for PoS, case, mood, lemma on those features' function probabili­ ties, but also uses topological features like function/PoS n-grams, barrier tags and daughter-sequences. In the CoNLL shared task, performance was below average on at­ tachment scores, but a relatively higher score for function tags/deprels in isolation suggests that the system's strengths were not fully exploited in the current architecture.