Advanced Semantics for Commonsense Knowledge Extraction

11/02/2020
by   Tuan-Phong Nguyen, et al.
15

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.

READ FULL TEXT
research
11/30/2021

Refined Commonsense Knowledge from Large-Scale Web Contents

Commonsense knowledge (CSK) about concepts and their properties is usefu...
research
05/27/2019

Commonsense Properties from Query Logs and Question Anwering Forums

Commonsense knowledge about object properties, human behavior and genera...
research
09/11/2021

Semantic Categorization of Social Knowledge for Commonsense Question Answering

Large pre-trained language models (PLMs) have led to great success on va...
research
05/27/2019

Commonsense Properties from Query Logs and Question Answering Forums

Commonsense knowledge about object properties, human behavior and genera...
research
05/28/2021

Inside ASCENT: Exploring a Deep Commonsense Knowledge Base and its Usage in Question Answering

ASCENT is a fully automated methodology for extracting and consolidating...
research
04/28/2020

R^3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge

We propose an unsupervised approach for sarcasm generation based on a no...
research
10/14/2022

Extracting Cultural Commonsense Knowledge at Scale

Structured knowledge is important for many AI applications. Commonsense ...

Please sign up or login with your details

Forgot password? Click here to reset