Braid: Weaving Symbolic and Neural Knowledge into Coherent Logical Explanations
Aditya Kalyanpur, Thomas Breloff, David Ferrucci
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.
中文速览
传统符号推理系统虽然精确、可解释，却有三大硬伤：依赖精确匹配导致脆性推理、无法处理不确定性、以及需要预先编码规则库。为此，研究者设计了一种名为 Braid 的新型逻辑推理引擎，核心创新在于两点：一是用神经网络驱动的"模糊统一函数"（custom unifiers）替代传统的精确匹配，允许在语义相近但字面不同的概念之间建立得分映射；二是引入"动态规则生成器"（dynamic rule generators），在推理时根据上下文即时生成可解释的因果规则，而非依赖预先手写的知识库。整个系统以分布式任务框架并行构建证明图，并在 ROC Story Cloze 故事理解测试上取得了接近当时最优的成绩，同时能为每个推理结论输出完整的逻辑解释链。这项工作的价值在于它走出了一条神经与符号融合的中间路线——既保留了符号系统透明可解释的优势，又借助神经模型弥补了知识缺口和语言多样性带来的匹配难题，为可解释 AI 推理提供了一个实用框架。
原文 arXiv:2011.13354;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2011.13354v4