Knowledge Completion for Generics using Guided Tensor Factorization

TL;DR

This paper introduces a novel knowledge guided tensor factorization method for completing generics knowledge bases, effectively inferring new facts with high precision and leveraging external schemas and taxonomies to improve learning and annotation efficiency.

Contribution

It presents the first successful approach for generics KB completion, utilizing external information and a taxonomy-guided active learning method to enhance inference about rare entities.

Findings

Achieves 80% precision on generics KBs, doubling their size.

State-of-the-art results with 74-86% precision.

Active learning method is 6x more effective for rare entities.

Abstract

Given a knowledge base or KB containing (noisy) facts about common nouns or generics, such as "all trees produce oxygen" or "some animals live in forests", we consider the problem of inferring additional such facts at a precision similar to that of the starting KB. Such KBs capture general knowledge about the world, and are crucial for various applications such as question answering. Different from commonly studied named entity KBs such as Freebase, generics KBs involve quantification, have more complex underlying regularities, tend to be more incomplete, and violate the commonly used locally closed world assumption (LCWA). We show that existing KB completion methods struggle with this new task, and present the first approach that is successful. Our results demonstrate that external information, such as relation schemas and entity taxonomies, if used appropriately, can be a surprisingly powerful tool in this setting. First, our simple yet effective knowledge guided tensor factorization approach achieves state-of-the-art results on two generics KBs (80% precise) for science, doubling their size at 74%-86% precision. Second, our novel taxonomy guided, submodular, active learning method for collecting annotations about rare entities (e.g., oriole, a bird) is 6x more effective at inferring further new facts about them than multiple active learning baselines.