Significance tests for the evaluation of ranking methods

Conference contribution
(Conference Contribution)


Publication Details

Author(s): Evert S
Publishing place: Geneva, Switzerland
Publication year: 2004
Conference Proceedings Title: Proceedings of the 20th International Conference on Computational Linguistics (Coling 2004)
Pages range: 945-951
Language: English


Abstract


This paper presents a statistical model that interprets the evaluation of ranking methods as a random experiment. This model predicts the variability of evaluation results, so that appropriate significance tests for the results can be derived. The paper concludes with an empirical validation of the model on a collocation extraction task.



FAU Authors / FAU Editors

Evert, Stefan Prof. Dr.
Lehrstuhl für Korpus- und Computerlinguistik


How to cite

APA:
Evert, S. (2004). Significance tests for the evaluation of ranking methods. In Proceedings of the 20th International Conference on Computational Linguistics (Coling 2004) (pp. 945-951). Geneva, Switzerland.

MLA:
Evert, Stefan. "Significance tests for the evaluation of ranking methods." Proceedings of the Proceedings of the 20th International Conference on Computational Linguistics (Coling 2004) Geneva, Switzerland, 2004. 945-951.

BibTeX: 

Last updated on 2018-11-08 at 00:10