arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.08176cs.CLcs.AI
收藏

基于多跳英语问句的知识查询

Querying Knowledge via Multi-Hop English Questions

Stony Brook University(石溪大学)

Tiantian Gao, Paul Fodor, Michael Kifer

摘要:

知识规范的固有困难和缺乏训练有素的专家是使基于知识表示和推理(KRR)范式的智能系统变得普遍的一些关键障碍。使用自然语言,特别是受控自然语言(CNL)的知识和查询创作是一种有前途的方法,可以使领域专家,谁不是训练有素的逻辑学家,既创建形式知识,又查询它。我们引入了KALM系统(知识创作逻辑机)支持知识创作(以及简单的查询)具有非常高的准确性,这是目前通过机器学习方法无法实现的。本文对KALM的问答方面进行了扩展,并介绍了能够回答更复杂的英语问题的KALM-QA(KALM for问答)。我们发现,KALM-QA在一系列与电影相关的问题上达到了100%的准确率,这些问题被称为MetaQA,其中包含近29,000个测试问题和超过260,000个训练问题。我们将其与已发表的机器学习方法进行了对比,后者远远达不到这一高分。

英文摘要:

The inherent difficulty of knowledge specification and the lack of trained specialists are some of the key obstacles on the way to making intelligent systems based on the knowledge representation and reasoning (KRR) paradigm commonplace. Knowledge and query authoring using natural language, especially controlled natural language (CNL), is one of the promising approaches that could enable domain experts, who are not trained logicians, to both create formal knowledge and query it. In previous work, we introduced the KALM system (Knowledge Authoring Logic Machine) that supports knowledge authoring (and simple querying) with very high accuracy that at present is unachievable via machine learning approaches. The present paper expands on the question answering aspect of KALM and introduces KALM-QA (KALM for Question Answering) that is capable of answering much more complex English questions. We show that KALM-QA achieves 100% accuracy on an extensive suite of movie-related questions, called MetaQA, which contains almost 29,000 test questions and over 260,000 training questions. We contrast this with a published machine learning approach, which falls far short of this high mark.

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。

↑