Error Mining with Suspicion Trees: Seeing the Forest for the Trees

Shashi Narayan 1 Claire Gardent 1
1 SYNALP - Natural Language Processing : representations, inference and semantics
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : In recent years, error mining approaches have been proposed to identify the most likely sources of errors in symbolic parsers and generators. However the techniques used generate a flat list of suspicious forms ranked by decreasing order of suspicion. We introduce a novel algorithm that structures the output of error mining into a tree (called, suspicion tree) highlighting the relationships between suspicious forms. We illustrate the impact of our approach by applying it to detect and analyse the most likely sources of failure in surface realisation; and we show how the suspicion tree built by our algorithm helps presenting the errors identified by error mining in a linguistically meaningful way thus providing better support for error analysis. The right frontier of the tree highlights the relative importance of the main error cases while the subtrees of a node indicate how a given error case divides into smaller more specific cases
Type de document :
Communication dans un congrès
24th International Conference on Computational Linguistics, Dec 2012, Mumbai, India. pp.60-73, 2012
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00768227
Contributeur : Claire Gardent <>
Soumis le : vendredi 21 décembre 2012 - 09:22:39
Dernière modification le : mardi 24 avril 2018 - 13:33:21
Document(s) archivé(s) le : vendredi 22 mars 2013 - 03:45:44

Fichier

nargar_coling12_error_mining_f...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00768227, version 1

Collections

Citation

Shashi Narayan, Claire Gardent. Error Mining with Suspicion Trees: Seeing the Forest for the Trees. 24th International Conference on Computational Linguistics, Dec 2012, Mumbai, India. pp.60-73, 2012. 〈hal-00768227〉

Partager

Métriques

Consultations de la notice

487

Téléchargements de fichiers

116