Syntactic Nuclei in Dependency Parsing – A Multilingual Exploration

01/28/2021
by   Ali Basirat, et al.
0

Standard models for syntactic dependency parsing take words to be the elementary units that enter into dependency relations. In this paper, we investigate whether there are any benefits from enriching these models with the more abstract notion of nucleus proposed by Tesnière. We do this by showing how the concept of nucleus can be defined in the framework of Universal Dependencies and how we can use composition functions to make a transition-based dependency parser aware of this concept. Experiments on 12 languages show that nucleus composition gives small but significant improvements in parsing accuracy. Further analysis reveals that the improvement mainly concerns a small number of dependency relations, including nominal modifiers, relations of coordination, main predicates, and direct objects.

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
03/31/2020

Inherent Dependency Displacement Bias of Transition-Based Algorithms

A wide variety of transition-based algorithms are currently used for dep...
research
02/22/2017

Improving a Strong Neural Parser with Conjunction-Specific Features

While dependency parsers reach very high overall accuracy, some dependen...
research
01/10/2022

Informal Persian Universal Dependency Treebank

This paper presents the phonological, morphological, and syntactic disti...
research
01/25/2023

Weakly Supervised Headline Dependency Parsing

English news headlines form a register with unique syntactic properties ...
research
05/21/2023

A Pilot Study on Dialogue-Level Dependency Parsing for Chinese

Dialogue-level dependency parsing has received insufficient attention, e...
research
06/08/2021

A Modest Pareto Optimisation Analysis of Dependency Parsers in 2021

We evaluate three leading dependency parser systems from different parad...

Please sign up or login with your details

Forgot password? Click here to reset