Conference Papers Year : 2017

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.

Fichier principal
Vignette du fichier
K17-3017.pdf (158.07 Ko) Télécharger le fichier
Origin Publisher files allowed on an open archive
Licence
Loading...

Dates and versions

hal-01622880 , version 1 (24-10-2017)

Licence

Identifiers

Cite

Lauriane Aufrant, Guillaume Wisniewski. LIMSI@CoNLL'17: UD Shared Task. Conference on Computational Natural Language Learning, Association for computational linguistics, Aug 2017, Vancouver, Canada. pp.163-173, ⟨10.18653/v1/K17-3017⟩. ⟨hal-01622880⟩
180 View
226 Download

Altmetric

Share

  • More