Measuring Contextual Fitness Using Error Contexts Extracted from the Wikipedia Revision History

Zesch, Torsten

doi:10.17185/duepublico/72182

Tagungsbeitrag 2012 CC BY-NC-SA 3.0

Veröffentlicht

Measuring Contextual Fitness Using Error Contexts Extracted from the Wikipedia Revision History

We evaluate measures of contextual fitness on the task of detecting real-word spelling errors. For that purpose, we extract naturally occurring errors and their context from the Wikipedia revision history. We show that such natural errors are better suited for evaluation than the previously used artificially created errors. In particular, the precision of statistical methods has been largely over-estimated, while the precision of knowledge-based approaches has been under-estimated. Additionally, we show that knowledge-based approaches can be improved by using semantic relatedness measures that make use of knowledge beyond classical taxonomic relations. Finally, we show that statistical and knowledge-based methods can be combined for increased performance.

Vorschau

Einordnung

Konferenz:: 13th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2012, April 23 - 27 2012 Avignon France
Datum der Veröffentlichung:: 2012
URN:: urn:nbn:de:hbz:464-20211027-143426-8
DOI:: 10.17185/duepublico/72182
Sprache:: Englisch
Ressourcentyp:: Text
Kollektion:: E-Publikationen
Sachgruppen der Deutschen Nationalbibliographie:: 004 Informatik
Link URL:: https://aclanthology.org/E12-1054
Einrichtung:: Fakultät für Ingenieurwissenschaften, Informatik und Angewandte Kognitionswissenschaft, Informatik, Sprachtechnologie
Abgrenzungspolitik:: Zesch, Torsten (2012): Measuring Contextual Fitness Using Error Contexts Extracted from the Wikipedia Revision History. In: Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2012), pp. 529–538. Association for Computational Linguistics. https://aclanthology.org/E12-1054