Parsing Universal Dependencies without training

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

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

Abstrakt

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.
OriginalsprogEngelsk
TitelProceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics
ForlagAssociation for Computational Linguistics
Publikationsdato2017
Sider230-240
ISBN (Elektronisk)978-1-945626-34-0
StatusUdgivet - 2017
BegivenhedThe 15th Conference of the European Chapter of the Association for Computational Linguistics - Valencia, Spanien
Varighed: 3 apr. 20177 apr. 2017
http://eacl2017.org/

Konference

KonferenceThe 15th Conference of the European Chapter of the Association for Computational Linguistics
Land/OmrådeSpanien
ByValencia
Periode03/04/201707/04/2017
Internetadresse

Fingeraftryk

Dyk ned i forskningsemnerne om 'Parsing Universal Dependencies without training'. Sammen danner de et unikt fingeraftryk.

Citationsformater