Real Anaphora Resolution Is Hard

Manfred Klenner; Angela Fahrni; Rico Sennrich

doi:10.1007/978-3-642-15760-8_15

Real Anaphora Resolution Is Hard

Manfred Klenner, Angela Fahrni, Rico Sennrich

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English
Title of host publication	Text, Speech and Dialogue
Subtitle of host publication	13th International Conference, TSD 2010, Brno, Czech Republic, September 6-10, 2010. Proceedings
Editors	Petr Sojka, Aleš Horák, Ivan Kopeček, Karel Pala
Publisher	Springer
Pages	109-116
Number of pages	8
ISBN (Electronic)	978-3-642-15760-8
ISBN (Print)	978-3-642-15759-2
DOIs	https://doi.org/10.1007/978-3-642-15760-8_15
Publication status	Published - 2010

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Berlin Heidelberg
Volume	6231
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Access to Document

10.1007/978-3-642-15760-8_15

Real Anaphora Resolution is HardAccepted author manuscript, 1.02 MB

http://link.springer.com/chapter/10.1007%2F978-3-642-15760-8_15

Cite this

Klenner, M., Fahrni, A., & Sennrich, R. (2010). Real Anaphora Resolution Is Hard. In P. Sojka, A. Horák, I. Kopeček, & K. Pala (Eds.), Text, Speech and Dialogue: 13th International Conference, TSD 2010, Brno, Czech Republic, September 6-10, 2010. Proceedings (pp. 109-116). Article Chapter 15 (Lecture Notes in Computer Science; Vol. 6231). Springer. https://doi.org/10.1007/978-3-642-15760-8_15

@inproceedings{a4d8552cbfc4400b981d84c3280d3e83,

title = "Real Anaphora Resolution Is Hard",

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. ",

author = "Manfred Klenner and Angela Fahrni and Rico Sennrich",

year = "2010",

doi = "10.1007/978-3-642-15760-8_15",

language = "English",

isbn = "978-3-642-15759-2",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "109--116",

editor = "Petr Sojka and Hor{\'a}k, { Ale{\v s}} and Kope{\v c}ek, { Ivan} and Karel Pala",

booktitle = "Text, Speech and Dialogue",

address = "United Kingdom",

}

Klenner, M, Fahrni, A & Sennrich, R 2010, Real Anaphora Resolution Is Hard. in P Sojka, A Horák, I Kopeček & K Pala (eds), Text, Speech and Dialogue: 13th International Conference, TSD 2010, Brno, Czech Republic, September 6-10, 2010. Proceedings., Chapter 15, Lecture Notes in Computer Science, vol. 6231, Springer, pp. 109-116. https://doi.org/10.1007/978-3-642-15760-8_15

Real Anaphora Resolution Is Hard. / Klenner, Manfred; Fahrni, Angela; Sennrich, Rico.
Text, Speech and Dialogue: 13th International Conference, TSD 2010, Brno, Czech Republic, September 6-10, 2010. Proceedings. ed. / Petr Sojka; Aleš Horák; Ivan Kopeček; Karel Pala. Springer, 2010. p. 109-116 Chapter 15 (Lecture Notes in Computer Science; Vol. 6231).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Real Anaphora Resolution Is Hard

AU - Klenner, Manfred

AU - Fahrni, Angela

AU - Sennrich, Rico

PY - 2010

Y1 - 2010

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-642-15760-8_15

DO - 10.1007/978-3-642-15760-8_15

M3 - Conference contribution

SN - 978-3-642-15759-2

T3 - Lecture Notes in Computer Science

SP - 109

EP - 116

BT - Text, Speech and Dialogue

A2 - Sojka, Petr

A2 - Horák, Aleš

A2 - Kopeček, Ivan

A2 - Pala, Karel

PB - Springer

ER -

Real Anaphora Resolution Is Hard

Abstract

Publication series

Access to Document

Fingerprint

Cite this