Advanced Semantics for Commonsense Knowledge Extraction

TL;DR

This paper introduces Ascent, a novel methodology for building a large-scale commonsense knowledge base with advanced expressiveness, capturing complex concepts and semantic facets, achieving better precision and recall than previous approaches.

Contribution

Ascent combines open information extraction with language models to automatically create a more expressive and accurate commonsense knowledge base than prior methods.

Findings

Ascent's KB is larger and of higher quality than previous collections.

Intrinsic evaluation confirms superior size and quality of Ascent KB.

Extrinsic evaluation shows improved performance in QA tasks using Ascent.

Abstract

Commonsense knowledge (CSK) about concepts and their properties is useful for AI applications such as robust chatbots. Prior works like ConceptNet, TupleKB and others compiled large CSK collections, but are restricted in their expressiveness to subject-predicate-object (SPO) triples with simple concepts for S and monolithic strings for P and O. Also, these projects have either prioritized precision or recall, but hardly reconcile these complementary goals. This paper presents a methodology, called Ascent, to automatically build a large-scale knowledge base (KB) of CSK assertions, with advanced expressiveness and both better precision and recall than prior works. Ascent goes beyond triples by capturing composite concepts with subgroups and aspects, and by refining assertions with semantic facets. The latter are important to express temporal and spatial validity of assertions and further qualifiers. Ascent combines open information extraction with judicious cleaning using language models. Intrinsic evaluation shows the superior size and quality of the Ascent KB, and an extrinsic evaluation for QA-support tasks underlines the benefits of Ascent. A web interface, data and code can be found at https://ascent.mpi-inf.mpg.de/.