Parsing Universal Dependencies without training - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2017

Parsing Universal Dependencies without training

Abstract

We propose UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of head attachment rules. It features two-step decoding to guarantee that function words are attached as leaf nodes. The parser requires no training, and it is competitive with a delexicalized transfer system. UDP offers a linguistically sound unsupervised alternative to cross-lingual parsing for UD, which can be used as a baseline for such systems. The parser has very few parameters and is distinctly robust to domain change across languages.
Fichier principal
Vignette du fichier
alonso2017-parsing.pdf (182.49 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-01677405 , version 1 (08-01-2018)

Identifiers

  • HAL Id : hal-01677405 , version 1

Cite

Hector Martinez Alonso, Željko Agić, Barbara Plank, Anders Søgaard. Parsing Universal Dependencies without training. EACL 2017 - 15th Conference of the European Chapter of the Association for Computational Linguistics, Apr 2017, Valencia, Spain. pp.229 - 239. ⟨hal-01677405⟩

Collections

INRIA INRIA2
92 View
258 Download

Share

Gmail Facebook Twitter LinkedIn More