Supertagging-based Parsing with Linear Context-free Rewriting Systems

Thomas Ruprecht, Richard Mörbitz


Abstract
We present the first supertagging-based parser for linear context-free rewriting systems (LCFRS). It utilizes neural classifiers and outperforms previous LCFRS-based parsers in both accuracy and parsing speed by a wide margin. Our results keep up with the best (general) discontinuous parsers, particularly the scores for discontinuous constituents establish a new state of the art. The heart of our approach is an efficient lexicalization procedure which induces a lexical LCFRS from any discontinuous treebank. We describe a modification to usual chart-based LCFRS parsing that accounts for supertagging and introduce a procedure that transforms lexical LCFRS derivations into equivalent parse trees of the original treebank. Our approach is evaluated on the English Discontinuous Penn Treebank and the German treebanks Negra and Tiger.
Anthology ID:
2021.naacl-main.232
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2923–2935
Language:
URL:
https://aclanthology.org/2021.naacl-main.232
DOI:
10.18653/v1/2021.naacl-main.232
Bibkey:
Cite (ACL):
Thomas Ruprecht and Richard Mörbitz. 2021. Supertagging-based Parsing with Linear Context-free Rewriting Systems. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2923–2935, Online. Association for Computational Linguistics.
Cite (Informal):
Supertagging-based Parsing with Linear Context-free Rewriting Systems (Ruprecht & Mörbitz, NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.232.pdf
Optional supplementary code:
 2021.naacl-main.232.OptionalSupplementaryCode.zip
Video:
 https://aclanthology.org/2021.naacl-main.232.mp4