NERosetta for the Named Entity Multi-lingual Space - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

NERosetta for the Named Entity Multi-lingual Space

Cvetana Krstev
  • Fonction : Auteur
  • PersonId : 963257
Duško Vitas
  • Fonction : Auteur
  • PersonId : 963258

Résumé

Named Entity Recognition has been a hot topic in Natural Language Processing for more than fifteen years. A number of systems for various languages have been developed using different approaches and based on different named entity schemes and tagging strategies. We present the NERosetta web application that can be used for comparison of these various approaches applied to aligned texts (bitexts). In order to illustrate its functionalities, we have used one literary text, its 7 bi-texts involving 5 languages and 5 different NER systems. We present some preliminary results and give guidelines for further development.
Fichier non déposé

Dates et versions

hal-01621019 , version 1 (22-10-2017)

Identifiants

  • HAL Id : hal-01621019 , version 1

Citer

Cvetana Krstev, Anđelka Zečević, Duško Vitas, Tita Kyriacopoulou. NERosetta for the Named Entity Multi-lingual Space. 6th Language & Technology Conference, Oct 2013, Poznan, Poland. pp.327-340. ⟨hal-01621019⟩
130 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More