Graphene: A Context-Preserving Open Information Extraction System

TL;DR

Graphene is an open information extraction system that produces context-preserving, semantically rich propositions from complex sentences, improving downstream semantic applications.

Contribution

It introduces a novel lightweight semantic representation that maintains context and rhetorical relations, enhancing the expressiveness of extracted propositions.

Findings

Produces accurate, meaningful propositions from complex sentences

Preserves context and rhetorical relations between extracted facts

Enhances downstream semantic applications

Abstract

We introduce Graphene, an Open IE system whose goal is to generate accurate, meaningful and complete propositions that may facilitate a variety of downstream semantic applications. For this purpose, we transform syntactically complex input sentences into clean, compact structures in the form of core facts and accompanying contexts, while identifying the rhetorical relations that hold between them in order to maintain their semantic relationship. In that way, we preserve the context of the relational tuples extracted from a source sentence, generating a novel lightweight semantic representation for Open IE that enhances the expressiveness of the extracted propositions.