Parsers know best: German PP attachment revisited

Do, Bich-Ngoc ; Rehbein, Ines

[img] PDF
2020.coling-main.185.pdf - Published

Download (283kB)

Additional URL:
URN: urn:nbn:de:bsz:180-madoc-578735
Document Type: Conference or workshop publication
Year of publication: 2020
Book title: COLING 2020 : The 28th International Conferenceon Computational Linguistics, proceedings of the conference, December 8-13, 2020, Barcelona, Spain (Online)
Page range: 2049-2061
Conference title: COLING 2020
Location of the conference venue: Online
Date of the conference: 08.-13.12.2020
Publisher: Scott, Donia
Place of publication: New York, NY
Publishing house: ACM Digital Library
ISBN: 978-1-952148-27-9
Publication language: English
Institution: Außerfakultäre Einrichtungen > SFB 884
Pre-existing license: Creative Commons Attribution 4.0 International (CC BY 4.0)
Subject: 004 Computer science, internet
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.

Dieser Eintrag ist Teil der Universitätsbibliographie.

Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.

Metadata export


+ Search Authors in

+ Download Statistics

Downloads per month over past year

View more statistics

You have found an error? Please let us know about your desired correction here: E-Mail

Actions (login required)

Show item Show item