The ParisNLP entry at the ConLL UD Shared Task 2017: A Tale of a #ParsingTragedy

Abstract : We present the ParisNLP entry at the UD CoNLL 2017 parsing shared task. In addition to the UDpipe models provided, we built our own data-driven tokenization models, sentence segmenter and lexicon-based morphological analyzers. All of these were used with a range of different parsing models (neural or not, feature-rich or not, transition or graph-based, etc.) and the best combination for each language was selected. Unfortunately, a glitch in the shared task's Matrix led our model selector to run generic, weakly lexicalized models , tailored for surprise languages, instead of our dataset-specific models. Because of this #ParsingTragedy, we officially ranked 27th, whereas our real models finally unofficially ranked 6th.
Type de document :
Communication dans un congrès
Conference on Computational Natural Language Learning, Aug 2017, Vancouver, Canada. pp.243-252, 2017, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. 〈http://universaldependencies.org/conll17/〉. 〈10.18653/v1/K17-3026〉
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01584168
Contributeur : Benoît Sagot <>
Soumis le : vendredi 8 septembre 2017 - 14:18:24
Dernière modification le : mardi 24 octobre 2017 - 13:35:51

Fichier

ParsingTragedy.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Éric Villemonte de La Clergerie, Benoît Sagot, Djamé Seddah. The ParisNLP entry at the ConLL UD Shared Task 2017: A Tale of a #ParsingTragedy. Conference on Computational Natural Language Learning, Aug 2017, Vancouver, Canada. pp.243-252, 2017, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. 〈http://universaldependencies.org/conll17/〉. 〈10.18653/v1/K17-3026〉. 〈hal-01584168〉

Partager

Métriques

Consultations de la notice

85

Téléchargements de fichiers

17