The ParisNLP entry at the ConLL UD Shared Task 2017: A Tale of a #ParsingTragedy - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

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

Résumé

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.
Fichier principal
Vignette du fichier
ParsingTragedy.pdf (300.64 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01584168 , version 1 (08-09-2017)

Identifiants

Citer

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, ⟨10.18653/v1/K17-3026⟩. ⟨hal-01584168⟩
161 Consultations
258 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More