The ADAPT Enhanced Dependency Parser at the IWPT 2020 Shared Task

TL;DR

The paper presents the ADAPT system for enhanced dependency parsing in multiple languages, utilizing a pipeline approach with heuristics and semantic parsers, achieving improved scores after a post-competition fix.

Contribution

It introduces a pipeline-based method combining UDPipe tools and heuristics for enhanced dependency parsing across 17 languages, with a focus on semantic dependency parsing.

Findings

Semantic dependency parser effective for enhanced dependencies

Last-minute fix significantly improved evaluation scores

Pipeline approach achieved top-tier performance after adjustments

Abstract

We describe the ADAPT system for the 2020 IWPT Shared Task on parsing enhanced Universal Dependencies in 17 languages. We implement a pipeline approach using UDPipe and UDPipe-future to provide initial levels of annotation. The enhanced dependency graph is either produced by a graph-based semantic dependency parser or is built from the basic tree using a small set of heuristics. Our results show that, for the majority of languages, a semantic dependency parser can be successfully applied to the task of parsing enhanced dependencies. Unfortunately, we did not ensure a connected graph as part of our pipeline approach and our competition submission relied on a last-minute fix to pass the validation script which harmed our official evaluation scores significantly. Our submission ranked eighth in the official evaluation with a macro-averaged coarse ELAS F1 of 67.23 and a treebank average of 67.49. We later implemented our own graph-connecting fix which resulted in a score of 79.53 (language average) or 79.76 (treebank average), which would have placed fourth in the competition evaluation.