Braid: Weaving Symbolic and Neural Knowledge into Coherent Logical Explanations

TL;DR

Braid is a novel logical reasoner that integrates symbolic and neural knowledge, supporting probabilistic rules and dynamic rule generation to produce coherent explanations and handle uncertainty.

Contribution

It introduces Braid, a reasoning framework combining symbolic and neural methods with probabilistic rules and dynamic rule generation for improved logical explanations.

Findings

Achieves near state-of-the-art results on ROC Story Cloze test

Provides coherent, frame-based explanations for reasoning tasks

Supports probabilistic reasoning and dynamic rule creation

Abstract

Traditional symbolic reasoning engines, while attractive for their precision and explicability, have a few major drawbacks: the use of brittle inference procedures that rely on exact matching (unification) of logical terms, an inability to deal with uncertainty, and the need for a precompiled rule-base of knowledge (the "knowledge acquisition" problem). To address these issues, we devise a novel logical reasoner called Braid, that supports probabilistic rules, and uses the notion of custom unification functions and dynamic rule generation to overcome the brittle matching and knowledge-gap problem prevalent in traditional reasoners. In this paper, we describe the reasoning algorithms used in Braid, and their implementation in a distributed task-based framework that builds proof/explanation graphs for an input query. We use a simple QA example from a children's story to motivate Braid's design and explain how the various components work together to produce a coherent logical explanation. Finally, we evaluate Braid on the ROC Story Cloze test and achieve close to state-of-the-art results while providing frame-based explanations.