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

TL;DR

This paper introduces ASCENT, a comprehensive web-based platform that extracts, consolidates, and explores a rich commonsense knowledge base from web content, enhancing question answering with semantic facets and composite concepts.

Contribution

It presents a novel automated method for building a detailed commonsense knowledge base with semantic facets, and provides an interactive portal for exploration and application in question answering.

Findings

Enhanced question answering performance demonstrated

Rich semantic facets improve knowledge representation

Interactive portal facilitates understanding and usage

Abstract

ASCENT is a fully automated methodology for extracting and consolidating commonsense assertions from web contents (Nguyen et al., WWW 2021). It advances traditional triple-based commonsense knowledge representation by capturing semantic facets like locations and purposes, and composite concepts, i.e., subgroups and related aspects of subjects. In this demo, we present a web portal that allows users to understand its construction process, explore its content, and observe its impact in the use case of question answering. The demo website and an introductory video are both available online.