DepDist: Surface realization via regex and learned dependency-distance tolerance

William Dyer


Abstract
This paper describes a method of inflecting and linearizing a lemmatized dependency tree by: (1) determining a regular expression and substitution to describe each productive wordform rule; (2) learning the dependency distance tolerance for each head-dependent pair, resulting in an edge-weighted directed acyclic graph (DAG); and (3) topologically sorting the DAG into a surface realization based on edge weight. The method’s output for 11 languages across 18 treebanks is competitive with the other submissions to the Second Multilingual Surface Realization Shared Task (SR ‘19).
Anthology ID:
D19-6303
Volume:
Proceedings of the 2nd Workshop on Multilingual Surface Realisation (MSR 2019)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Simon Mille, Anja Belz, Bernd Bohnet, Yvette Graham, Leo Wanner
Venue:
WS
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
25–34
Language:
URL:
https://aclanthology.org/D19-6303
DOI:
10.18653/v1/D19-6303
Bibkey:
Cite (ACL):
William Dyer. 2019. DepDist: Surface realization via regex and learned dependency-distance tolerance. In Proceedings of the 2nd Workshop on Multilingual Surface Realisation (MSR 2019), pages 25–34, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
DepDist: Surface realization via regex and learned dependency-distance tolerance (Dyer, 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-6303.pdf