Parsing Universal Dependencies without training

Héctor Martínez Alonso, Zeljko Agic, Barbara Plank, Anders Søgaard

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Abstract

We present UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of specific dependency head rules. UDP 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. The parser has very few parameters and distinctly robust to domain change across languages.
Original languageEnglish
Title of host publicationProceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics
PublisherAssociation for Computational Linguistics
Publication date2017
Pages230-240
ISBN (Electronic)978-1-945626-34-0
Publication statusPublished - 2017
EventThe 15th Conference of the European Chapter of the Association for Computational Linguistics - Valencia, Spain
Duration: 3 Apr 20177 Apr 2017
http://eacl2017.org/

Conference

ConferenceThe 15th Conference of the European Chapter of the Association for Computational Linguistics
Country/TerritorySpain
CityValencia
Period03/04/201707/04/2017
Internet address

Fingerprint

Dive into the research topics of 'Parsing Universal Dependencies without training'. Together they form a unique fingerprint.

Cite this