Parsing Universal Dependencies without training

Hector Martinez Alonso (1) , Željko Agić (2) , Barbara Plank (3) , Anders Søgaard (4)

1 ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities
2 ITU - IT University of Copenhagen
3 CLCG - Center for Language and Cognition
4 UCPH - University of Copenhagen = Københavns Universitet

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.

Domaines: Informatique et langage [cs.CL]

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⟩