Getting More Out Of Syntax with PropS

TL;DR

PropS is a new representation and tool that extracts explicit propositional structures from dependency trees to improve semantic NLP applications by reducing heuristic post-processing and information loss.

Contribution

The paper introduces PropS, a novel output representation and extraction tool that explicitly captures propositional structures from dependency trees for semantic NLP.

Findings

PropS improves the extraction of propositional structures from syntax.

The tool reduces reliance on heuristic post-processing.

Enhanced semantic understanding from dependency trees.

Abstract

Semantic NLP applications often rely on dependency trees to recognize major elements of the proposition structure of sentences. Yet, while much semantic structure is indeed expressed by syntax, many phenomena are not easily read out of dependency trees, often leading to further ad-hoc heuristic post-processing or to information loss. To directly address the needs of semantic applications, we present PropS -- an output representation designed to explicitly and uniformly express much of the proposition structure which is implied from syntax, and an associated tool for extracting it from dependency trees.