An evaluation model for systems and resources employed in the correction of errors in textual documents

Arnaud Renard 1 Sylvie Calabretto 1 Béatrice Rumpler 1
1 DRIM - Distribution, Recherche d'Information et Mobilité
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : The wide adoption of Web 2.0 services has resulted in an increase in the amount of information produced. The quantity of errors contained in such information has grown even faster. Indeed, in traditional information production process documents were produced by professionals while in the Web context the content is generated by the users themselves. It is therefore necessary to take into account the errors particularly when such systems need to manage information of variable quality. Our state of the art leads us to identify difficulties in the comparative evaluation of error correction systems. Our proposal consists in an evaluation model for error correction systems and low-level string similarity (and distance) metrics they rely on. This model is implemented in an extensible platform providing a framework to evaluate those systems.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01354471
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Thursday, August 18, 2016 - 7:28:57 PM
Last modification on : Friday, January 11, 2019 - 4:35:34 PM

Identifiers

Citation

Arnaud Renard, Sylvie Calabretto, Béatrice Rumpler. An evaluation model for systems and resources employed in the correction of errors in textual documents. 8th International Workshop on Text-based Information Retrieval (TIR 2011) in conjunction with the 22nd International Conference on Database and Expert Systems Applications (DEXA 2011), Aug 2011, Toulouse, France, France. pp.160-164, ⟨10.1109/DEXA.2011.11⟩. ⟨hal-01354471⟩

Share

Metrics

Record views

142