Braid：将符号和神经知识编织成连贯的逻辑推理
Braid: Weaving Symbolic and Neural Knowledge into Coherent Logical Explanations
摘要：
传统的符号推理引擎，虽然有吸引力的精度和可解释性，有几个主要的缺点：使用脆弱的推理过程，依赖于精确匹配（统一）的逻辑术语，无法处理不确定性，并需要一个预编译的规则库的知识（“知识获取“的问题）。为了解决这些问题，我们设计了一种新的逻辑推理机称为辫子，支持概率规则，并使用自定义统一功能和动态规则生成的概念，以克服传统推理机中普遍存在的脆弱匹配和知识差距问题。在本文中，我们描述的推理算法中使用的辫子，并在一个分布式的基于任务的框架，建立证明/解释图的输入查询实现。我们使用一个来自儿童故事的简单QA示例来激发Braid的设计，并解释各种组件如何协同工作以产生连贯的逻辑解释。最后，我们在ROC故事完形填空测试中对Braid进行了评估，并在提供基于框架的解释的同时获得了接近最先进的结果。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
