Real Anaphora Resolution Is Hard

Manfred Klenner, Angela Fahrni, Rico Sennrich

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We introduce a system for anaphora resolution for German that uses various resources in order to develop a real system as opposed to systems based on idealized assumptions, e.g. the use of true mentions only or perfect parse trees and perfect morphology. The components that we use to replace such idealizations comprise a full-fledged morphology, a Wikipedia-based named entity recognition, a rule-based dependency parser and a German wordnet. We show that under these conditions coreference resolution is (at least for German) still far from being perfect.
Original languageEnglish
Title of host publicationText, Speech and Dialogue
Subtitle of host publication13th International Conference, TSD 2010, Brno, Czech Republic, September 6-10, 2010. Proceedings
EditorsPetr Sojka, Aleš Horák, Ivan Kopeček, Karel Pala
PublisherSpringer Berlin Heidelberg
Pages109-116
Number of pages8
ISBN (Electronic)978-3-642-15760-8
ISBN (Print)978-3-642-15759-2
DOIs
Publication statusPublished - 2010

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
Volume6231
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Cite this