LIMSI@CoNLL'17: UD Shared Task

Abstract : This paper describes LIMSI's submission to the CoNLL 2017 UD Shared Task, which is focused on small treebanks, and how to improve low-resourced parsing only by ad hoc combination of multiple views and resources. We present our approach for low-resourced parsing, together with a detailed analysisof the results for each test treebank. We also report extensive analysis experiments on model selection for the PUD treebanks, and on annotation consistency among UD treebanks.
Type de document :
Communication dans un congrès
Association for computational linguistics. Conference on Computational Natural Language Learning, Aug 2017, Vancouver, Canada. Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies,, pp.163-173, 2017, 〈10.18653/v1/K17-3017〉
Liste complète des métadonnées

Littérature citée [20 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01622880
Contributeur : Limsi Publications <>
Soumis le : mardi 24 octobre 2017 - 17:34:53
Dernière modification le : jeudi 11 janvier 2018 - 06:25:47
Document(s) archivé(s) le : jeudi 25 janvier 2018 - 14:40:53

Fichier

K17-3017.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Collections

Citation

Lauriane Aufrant, Guillaume Wisniewski. LIMSI@CoNLL'17: UD Shared Task. Association for computational linguistics. Conference on Computational Natural Language Learning, Aug 2017, Vancouver, Canada. Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies,, pp.163-173, 2017, 〈10.18653/v1/K17-3017〉. 〈hal-01622880〉

Partager

Métriques

Consultations de la notice

59

Téléchargements de fichiers

12