Parsing Universal Dependencies without training
- Héctor Martínez Alonso,
- Zeljko Agic,
- Barbara Plank,
- Anders Søgaard
- Paris Diderot University,
- ,
- ,
- University of Groningen,
- University of Copenhagen
Research Output:
Conference Article in Proceeding or Book/Report chapter
Article in proceedings
Peer-review
Open access
Publication Information
Output type
Research Output:
Conference Article in Proceeding or Book/Report chapter
Article in proceedings
Peer-reviewOriginal language
EnglishPages from-to (Number of pages)
Pages 230-240Publication milestones
- Published - 2017
Publication status
Published - 2017
Publisher
Association for Computational Linguistics, United StatesISBN (Electronic)
978-1-945626-34-0Publication IDs
- Scopus: 85021642092
Host publication title
Proceedings of the 15th Conference of the European Chapter of the Association for Computational LinguisticsAbstract
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.
Publication metrics
PlumX
Captures
104
Citations
11
Access to documents
Accepted author manuscript, 301.47 KB
Final published version
Related Event
Title
The 15th Conference of the European Chapter of the Association for Computational Linguistics
Event type
ConferenceLinks
Degree of recognition
International eventDate
03/04/2017 - 07/04/2017Location
ValenciaSpain