The First Shared Task on Discourse Representation Structure Parsing

TL;DR

This paper introduces the first shared task on Discourse Representation Structure parsing, focusing on semantic parsing of English sentences into rich, scoped meaning representations, and reports improved results over previous methods.

Contribution

It presents a new shared task for DRS parsing, providing a benchmark and demonstrating advancements in semantic parsing accuracy.

Findings

Improved DRS parsing performance over previous state-of-the-art.

Established a benchmark for DRS parsing tasks.

Highlighted the challenges of rich lexical and scope information in DRSs.

Abstract

The paper presents the IWCS 2019 shared task on semantic parsing where the goal is to produce Discourse Representation Structures (DRSs) for English sentences. DRSs originate from Discourse Representation Theory and represent scoped meaning representations that capture the semantics of negation, modals, quantification, and presupposition triggers. Additionally, concepts and event-participants in DRSs are described with WordNet synsets and the thematic roles from VerbNet. To measure similarity between two DRSs, they are represented in a clausal form, i.e. as a set of tuples. Participant systems were expected to produce DRSs in this clausal form. Taking into account the rich lexical information, explicit scope marking, a high number of shared variables among clauses, and highly-constrained format of valid DRSs, all these makes the DRS parsing a challenging NLP task. The results of the shared task displayed improvements over the existing state-of-the-art parser.