Acquiring Knowledge from Encyclopedic Texts

TL;DR

This paper presents SNOWY, a computational model that extracts and represents knowledge from encyclopedic texts, enabling question answering about animal classifications, habitats, and dietary habits.

Contribution

It introduces a novel system that automatically acquires and represents knowledge from unedited encyclopedic texts, including semantic interpretation and inference capabilities.

Findings

SNOWY successfully acquires new concepts and relations

The system can answer a wide range of questions about animal knowledge

Performance evaluation shows effective knowledge extraction and question answering

Abstract

A computational model for the acquisition of knowledge from encyclopedic texts is described. The model has been implemented in a program, called SNOWY, that reads unedited texts from {\em The World Book Encyclopedia}, and acquires new concepts and conceptual relations about topics dealing with the dietary habits of animals, their classifications and habitats. The program is also able to answer an ample set of questions about the knowledge that it has acquired. This paper describes the essential components of this model, namely semantic interpretation, inferences and representation, and ends with an evaluation of the performance of the program, a sample of the questions that it is able to answer, and its relation to other programs of similar nature.