Sentences with Gapping: Parsing and Reconstructing Elided Predicates

TL;DR

This paper introduces two methods for parsing sentences with gapping into Universal Dependencies graphs, explicitly encoding elided predicates, improving downstream natural language understanding tasks.

Contribution

The paper presents novel parsing methods that explicitly represent elided predicates in dependency graphs, enhancing the handling of gapping constructions across languages.

Findings

High accuracy in reconstructing elided material when gaps are correctly predicted

Both methods effectively encode elided predicates in dependency graphs

Method applicability demonstrated on Swedish language

Abstract

Sentences with gapping, such as Paul likes coffee and Mary tea, lack an overt predicate to indicate the relation between two or more arguments. Surface syntax representations of such sentences are often produced poorly by parsers, and even if correct, not well suited to downstream natural language understanding tasks such as relation extraction that are typically designed to extract information from sentences with canonical clause structure. In this paper, we present two methods for parsing to a Universal Dependencies graph representation that explicitly encodes the elided material with additional nodes and edges. We find that both methods can reconstruct elided material from dependency trees with high accuracy when the parser correctly predicts the existence of a gap. We further demonstrate that one of our methods can be applied to other languages based on a case study on Swedish.