Using Verb-Noun Patterns to Detect Process Inputs

Abstract : We present the preliminary results of an ongoing work aimed at using morpho-syntactic patterns to extract information from process descriptions in a semi-supervised manner. The experiments have been designed for generic information extraction tasks and evaluated on detecting ingredients from cooking recipes in French using a large gold standard corpus. The proposed method uses bi-lexical dependency oriented syntactic analysis of the text and extracts relevant morpho-syntactic patterns. Those patterns are then used as features for different machine learning methods to acquire the final ingredient list. Furthermore, this approach may easily be adapted to similar tasks since it relies on mining generic morpho-syntactic patterns from the documents automatically. The method itself is language independent, considering language specific parsers being used. The performance of our method on the DEFT 2013 data set is nevertheless satisfactory since it significantly outperforms the best system from the original challenge (0.75 vs 0.66 MAP).
Type de document :
Communication dans un congrès
Text Speech And Dialog, 2014, Brno, Czech Republic, France. Text Speech And Dialog, 2014
Liste complète des métadonnées

https://hal-inalco.archives-ouvertes.fr/hal-01359437
Contributeur : Damien Nouvel <>
Soumis le : vendredi 2 septembre 2016 - 13:08:55
Dernière modification le : mardi 17 juillet 2018 - 23:36:01

Identifiants

  • HAL Id : hal-01359437, version 1

Collections

Citation

Munshi Asadullah, Damien Nouvel, Patrick Paroubek. Using Verb-Noun Patterns to Detect Process Inputs. Text Speech And Dialog, 2014, Brno, Czech Republic, France. Text Speech And Dialog, 2014. 〈hal-01359437〉

Partager

Métriques

Consultations de la notice

107