AI Chat AI Image Generator AI Video Text to Speech

Efficient EUD Parsing

06/01/2020

∙

by Mathieu Dehouck, et al.

∙

∙

We present the system submission from the FASTPARSE team for the EUD Shared Task at IWPT 2020. We engaged with the task by focusing on efficiency. For this we considered training costs and inference efficiency. Our models are a combination of distilled neural dependency parsers and a rule-based system that projects UD trees into EUD graphs. We obtained an average ELAS of 74.04 for our official submission, ranking 4th overall.

Mathieu Dehouck
2 publications
Mark Anderson
15 publications
Carlos Gómez-Rodríguez
72 publications

page 1

page 2

page 3

page 4

research

∙ 06/24/2021

Splitting EUD graphs into trees: A quick and clatty approach

We present the system submission from the FASTPARSE team for the EUD Sha...

0 Mark Anderson, et al. ∙

research

∙ 07/08/2021

COMBO: a new module for EUD parsing

We introduce the COMBO-based approach for EUD parsing and its implementa...

0 Mateusz Klimaszewski, et al. ∙

research

∙ 03/15/2017

SyntaxNet Models for the CoNLL 2017 Shared Task

We describe a baseline dependency parsing system for the CoNLL2017 Share...

0 Chris Alberti, et al. ∙

research

∙ 06/02/2020

Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data

This paper presents the system used in our submission to the IWPT 2020 S...

0 Xinyu Wang, et al. ∙

research

∙ 04/26/2020

Semi-Supervised Neural System for Tagging, Parsing and Lematization

This paper describes the ICS PAS system which took part in CoNLL 2018 sh...

0 Piotr Rybak, et al. ∙

research

∙ 01/31/2022

POTATO: exPlainable infOrmation exTrAcTion framewOrk

We present POTATO, a task- and languageindependent framework for human-i...

0 Ádám Kovács, et al. ∙

research

∙ 06/01/2019

Abstract Predicate Entailment over Points-To Heaplets is Syntax Recognition

Abstract predicates are considered in this paper as abstraction techniqu...

0 René Haberland, et al. ∙