Automatic detection of causal relations in German multilogs

Zitieren

Dateien zu dieser Ressource

Prüfsumme: MD5:dd7184d9ac6eb44eb927e0b08eea3c7c

BÖGEL, Tina, Annette HAUTLI-JANISZ, Sebastian SULGER, Miriam BUTT, 2014. Automatic detection of causal relations in German multilogs. 14th Conference of the European Chapter of the Association for Computational Linguistics. Gothenburg, 26. Apr 2014. In: EACL 2014 : 14th Conference of the European Chapter of the Association for Computational Linguistics ; Proceedings of the Workshop on Computational Approaches to Causality in Language. 14th Conference of the European Chapter of the Association for Computational Linguistics. Gothenburg, 26. Apr 2014. Stroudsburg:Association for Computational Linguistics, pp. 20-27. ISBN 978-1-937284-86-2

@inproceedings{Bogel2014Autom-29255, title={Automatic detection of causal relations in German multilogs}, year={2014}, isbn={978-1-937284-86-2}, address={Stroudsburg}, publisher={Association for Computational Linguistics}, booktitle={EACL 2014 : 14th Conference of the European Chapter of the Association for Computational Linguistics ; Proceedings of the Workshop on Computational Approaches to Causality in Language}, pages={20--27}, author={Bögel, Tina and Hautli-Janisz, Annette and Sulger, Sebastian and Butt, Miriam} }

Sulger, Sebastian deposit-license Automatic detection of causal relations in German multilogs Bögel, Tina Hautli-Janisz, Annette Butt, Miriam 2014 2014-11-14T10:26:27Z Sulger, Sebastian eng Proceedings of the Workshop on Computational Approaches to Causality in Language : 14th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2014 ; April 26, 2014, Gothenburg, Sweden / Stroudsburg, PA : Association for Computational Linguistics (ACL), 2014. - S. 20-27. - ISBN 978-1-937284-86-2 This paper introduces a linguisticallymotivated, rule-based annotation system for causal discourse relations in transcripts of spoken multilogs in German. The overall aim is an automatic means of determining the degree of justification provided by a speaker in the delivery of an argument<br />in a multiparty discussion. The system comprises of two parts: A disambiguation module which differentiates causal connectors from their other senses, and a discourse relation annotation system which marks the spans of text that constitute the reason and the result/conclusion expressed<br />by the causal relation. The system is evaluated against a gold standard of German transcribed spoken dialogue. The results show that our system performs reliably well with respect to both tasks. Hautli-Janisz, Annette 2014-11-14T10:26:27Z Bögel, Tina Butt, Miriam

Dateiabrufe seit 14.11.2014 (Informationen über die Zugriffsstatistik)

Boegel_0-253693.pdf 174

Das Dokument erscheint in:

KOPS Suche


Stöbern

Mein Benutzerkonto