Parsers Know Best: German PP Attachment Revisited

Bich-Ngoc Do, Ines Rehbein


Abstract
In the paper, we revisit the PP attachment problem which has been identified as one of the major sources for parser errors and discuss shortcomings of recent work. In particular, we show that using gold information for the extraction of attachment candidates as well as a missing comparison of the system’s output to the output of a full syntactic parser leads to an overly optimistic assessment of the results. We address these issues by presenting a realistic evaluation of the potential of different PP attachment systems, using fully predicted information as system input. We compare our results against the output of a strong neural parser and show that the full parsing approach is superior to modeling PP attachment disambiguation as a separate task.
Anthology ID:
2020.coling-main.185
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2049–2061
Language:
URL:
https://aclanthology.org/2020.coling-main.185
DOI:
10.18653/v1/2020.coling-main.185
Bibkey:
Cite (ACL):
Bich-Ngoc Do and Ines Rehbein. 2020. Parsers Know Best: German PP Attachment Revisited. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2049–2061, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Parsers Know Best: German PP Attachment Revisited (Do & Rehbein, COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.185.pdf