A Simple Approach to Case-Based Reasoning in Knowledge Bases

Rajarshi Das, Ameya Godbole, Shehzaad Dhuliawala, Manzil Zaheer, Andrew McCallum

Keywords: case based reasoning, non-parametric reasoning, knowledge base completion

TL;DR: Learn to answer a query about an entity by gathering reasoning paths from other similar entities in the Knowledge Base

Subject Areas: Knowledge Representation, Semantic Web and Search, QuestionAnswering and Reasoning, Relational AI

Archival Status: Archival

Abstract:

We present a surprisingly simple yet accurate approach to reasoning in knowledge graphs (KGs) that requires \emph{no training}, and is reminiscent of case-based reasoning in classical artificial intelligence (AI).
Consider the task of finding a target entity given a source entity and a binary relation.
Our approach finds multiple \textit{graph path patterns} that connect similar source entities through the given relation, and looks for pattern matches starting from the query source.
Using our method, we obtain new state-of-the-art accuracy, outperforming all previous models, on NELL-995 and FB-122.
We also demonstrate that our model is robust in low data settings, outperforming recently proposed meta-learning approaches.