Real anaphora resolution is hard: the case of German

Authors:
Manfred Klenner;Angela Fahrni;Rico Sennrich
Affiliations:
Institute of Computational Linguistics, Zurich;-;Institute of Computational Linguistics, Zurich
Venue:
TSD'10 Proceedings of the 13th international conference on Text, speech and dialogue
Year:
2010

Citing 3
Cited 0

A machine learning approach to coreference resolution of noun phrases

Computational Linguistics - Special issue on computational anaphora resolution
Optimizing algorithms for pronoun resolution

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Optimization in coreference resolution is not needed: a nearly-optimal algorithm with intensional constraints

EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

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.