Lattice: Data Adaptation for Named Entity Recognition on Tweets with Features-Rich CRF - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Lattice: Data Adaptation for Named Entity Recognition on Tweets with Features-Rich CRF

Résumé

This article describes our CRF named entity extractor for Twitter data. We first discuss some specificities of the task, with an example found in the training data. Then we present how we built our CRF model, especially the way features were defined. The results of these first experiments are given. We also tested our model with dev 2015 data and we describe the procedure we have used to adapt older Twit-ter data to the data available for this 2015 shared task. Our final results for the task are discussed.

Domaines

Informatique
Fichier principal
Vignette du fichier
WNUT09.pdf (92.79 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01473392 , version 1 (21-02-2017)

Identifiants

  • HAL Id : hal-01473392 , version 1

Citer

Tian Tian, Marco Dinarelli, Isabelle Tellier. Lattice: Data Adaptation for Named Entity Recognition on Tweets with Features-Rich CRF. ACL 2015 workshop WNUT, Jul 2015, Beijing, China. ⟨hal-01473392⟩
89 Consultations
74 Téléchargements

Partager

Gmail Facebook X LinkedIn More