Evaluation Metrics for Automatic Temporal Annotation of Texts - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

Evaluation Metrics for Automatic Temporal Annotation of Texts

Résumé

Recent years have seen increasing attention in temporal processing of texts as well as a lot of standardization effort of temporal information in natural language. A central part of this information lies in the temporal relations between events described in a text, when their precise times or dates are not known. Reliable human annotation of such information is difficult, and automatic comparisons must follow procedures beyond mere precision-recall of local pieces of information, since a coherent picture can only be considered at a global level. We address the problem of evaluation metrics of such information, aiming at fair comparisons between systems, by proposing some measures taking into account the globality of a text.
Fichier non déposé

Dates et versions

hal-00292202 , version 1 (30-06-2008)

Identifiants

  • HAL Id : hal-00292202 , version 1

Citer

Xavier Tannier, Philippe Muller. Evaluation Metrics for Automatic Temporal Annotation of Texts. Sixth International Language Resources and Evaluation (LREC'08), 2008, Marrakech, Morocco. ⟨hal-00292202⟩
81 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More