COMBO: a new module for EUD parsing

TL;DR

This paper presents COMBO, a new module for Enhanced Universal Dependencies parsing, which predicts UD trees and EUD graphs, merging them into final structures, and was evaluated in the IWPT 2021 shared task.

Contribution

The paper introduces COMBO, a novel approach for EUD parsing that combines tree and graph predictions, extending edge labels with case information, and demonstrates competitive performance.

Findings

Achieved 83.79% ELAS in IWPT 2021 EUD shared task

Ranked fourth among participating systems

Source code publicly available

Abstract

We introduce the COMBO-based approach for EUD parsing and its implementation, which took part in the IWPT 2021 EUD shared task. The goal of this task is to parse raw texts in 17 languages into Enhanced Universal Dependencies (EUD). The proposed approach uses COMBO to predict UD trees and EUD graphs. These structures are then merged into the final EUD graphs. Some EUD edge labels are extended with case information using a single language-independent expansion rule. In the official evaluation, the solution ranked fourth, achieving an average ELAS of 83.79%. The source code is available at https://gitlab.clarin-pl.eu/syntactic-tools/combo.