Parsing Universal Dependencies without training

01/11/2017
by   Héctor Martínez Alonso, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/18/2017

Universal Dependencies Parsing for Colloquial Singaporean English

Singlish can be interesting to the ACL community both linguistically as ...
research
04/22/2022

Out-of-Domain Evaluation of Finnish Dependency Parsing

The prevailing practice in the academia is to evaluate the model perform...
research
05/24/2023

Structural Ambiguity and its Disambiguation in Language Model Based Parsers: the Case of Dutch Clause Relativization

This paper addresses structural ambiguity in Dutch relative clauses. By ...
research
05/29/2017

On Multilingual Training of Neural Dependency Parsers

We show that a recently proposed neural dependency parser can be improve...
research
10/10/2017

The Galactic Dependencies Treebanks: Getting More Data by Synthesizing New Languages

We release Galactic Dependencies 1.0---a large set of synthetic language...
research
07/16/2018

LATE Ain'T Earley: A Faster Parallel Earley Parser

We present the LATE algorithm, an asynchronous variant of the Earley alg...
research
06/03/2019

Phase-based Minimalist Parsing and complexity in non-local dependencies

A cognitively plausible parsing algorithm should perform like the human ...

Please sign up or login with your details

Forgot password? Click here to reset