Configurable Dependency Tree Extraction from CCG Derivations

Kilian Evang


Abstract
We revisit the problem of extracting dependency structures from the derivation structures of Combinatory Categorial Grammar (CCG). Previous approaches are often restricted to a narrow subset of CCG or support only one flavor of dependency tree. Our approach is more general and easily configurable, so that multiple styles of dependency tree can be obtained. In an initial case study, we show promising results for converting English, German, Italian, and Dutch CCG derivations from the Parallel Meaning Bank into (unlabeled) UD-style dependency trees.
Anthology ID:
2020.udw-1.10
Volume:
Proceedings of the Fourth Workshop on Universal Dependencies (UDW 2020)
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venues:
COLING | UDW
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
87–93
Language:
URL:
https://www.aclweb.org/anthology/2020.udw-1.10
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.udw-1.10.pdf