Hybrid Grammars for Parsing of Discontinuous Phrase Structures and Non-Projective Dependency Structures

Kilian Gebhardt, Mark-Jan Nederhof, Heiko Vogler


Abstract
We explore the concept of hybrid grammars, which formalize and generalize a range of existing frameworks for dealing with discontinuous syntactic structures. Covered are both discontinuous phrase structures and non-projective dependency structures. Technically, hybrid grammars are related to synchronous grammars, where one grammar component generates linear structures and another generates hierarchical structures. By coupling lexical elements of both components together, discontinuous structures result. Several types of hybrid grammars are characterized. We also discuss grammar induction from treebanks. The main advantage over existing frameworks is the ability of hybrid grammars to separate discontinuity of the desired structures from time complexity of parsing. This permits exploration of a large variety of parsing algorithms for discontinuous structures, with different properties. This is confirmed by the reported experimental results, which show a wide variety of running time, accuracy, and frequency of parse failures.
Anthology ID:
J17-3001
Volume:
Computational Linguistics, Volume 43, Issue 3 - September 2017
Month:
September
Year:
2017
Address:
Cambridge, MA
Venue:
CL
SIG:
Publisher:
MIT Press
Note:
Pages:
465–520
Language:
URL:
https://aclanthology.org/J17-3001
DOI:
10.1162/COLI_a_00291
Bibkey:
Cite (ACL):
Kilian Gebhardt, Mark-Jan Nederhof, and Heiko Vogler. 2017. Hybrid Grammars for Parsing of Discontinuous Phrase Structures and Non-Projective Dependency Structures. Computational Linguistics, 43(3):465–520.
Cite (Informal):
Hybrid Grammars for Parsing of Discontinuous Phrase Structures and Non-Projective Dependency Structures (Gebhardt et al., CL 2017)
Copy Citation:
PDF:
https://aclanthology.org/J17-3001.pdf
Data
Penn Treebank