Skip to Main content Skip to Navigation
Conference papers

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.
Document type :
Conference papers
Complete list of metadata

Cited literature [33 references]  Display  Hide  Download

https://hal.inria.fr/hal-01677405
Contributor : Benoît Sagot <>
Submitted on : Monday, January 8, 2018 - 3:18:23 PM
Last modification on : Wednesday, June 12, 2019 - 3:30:03 PM

File

alonso2017-parsing.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-01677405, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

196

Files downloads

535