Treebank Grammar Techniques for Non-Projective Dependency Parsing
2009 (English)In: Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics, Stroudsburg, PA, USA: Association for Computational Linguistics, 2009, 478-486 p.Conference paper (Refereed)
An open problem in dependency parsing is the accurate and efﬁcient treatment of non-projective structures. We propose to attack this problem using chart-parsing algorithms developed for mildly context-sensitive grammar formalisms. In this paper, we provide two key tools for this approach. First, we show how to reduce non-projective dependency parsing to parsing with Linear Context-Free Rewriting Systems (LCFRS), by presenting a technique for extracting LCFRS from dependency treebanks. For efﬁcient parsing, the extracted grammars need to be transformed in order to minimize the number of nonterminal symbols per production. Our second contribution is an algorithm that computes this transformation for a large, empirically relevant class of grammars.
Place, publisher, year, edition, pages
Stroudsburg, PA, USA: Association for Computational Linguistics, 2009. 478-486 p.
, Association for Computational Linguistics. European Chapter (EACL), ISSN 1525-2450
General Language Studies and Linguistics
Research subject Computational Linguistics
IdentifiersURN: urn:nbn:se:liu:diva-100293OAI: oai:DiVA.org:liu-100293DiVA: diva2:661445
Twelfth Conference of the European Chapter of the Association for Computational Linguistics (EACL), 30 March – 3 April 2009 Megaron Athens International Conference Centre Athens, Greece