Graphene: A Context-Preserving Open Information Extraction System
This work addresses the need for context-preserving extraction in Open IE to improve downstream semantic applications, representing an incremental advancement in the field.
The authors tackled the problem of generating accurate and meaningful propositions for Open Information Extraction by introducing Graphene, a system that transforms complex sentences into core facts with preserved context, resulting in a novel lightweight semantic representation that enhances proposition expressiveness.
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.