Declarative Question Answering over Knowledge Bases containing Natural Language Text with Answer Set Programming
Arindam Mitra‡ Peter Clark† Oyvind Tafjord† Chitta Baral‡ † Allen Institute for Artificial Intelligence, Seattle, WA, U.S.A. ‡ Arizona State University, AZ, U.S.A.
Abstract
While in recent years machine learning (ML) based approaches have been the popular approach in developing end-to-end question answering systems, such systems often struggle when additional knowledge is needed to correctly answer the questions. Proposed alternatives involve translating the question and the natural language text to a logical representation and then use logical reasoning. However, this alternative falters when the size of the text gets bigger. To address this we propose an approach that does logical reasoning over premises written in natural language text. The proposed method uses recent features of Answer Set Programming (ASP) to call external NLP modules (which may be based on ML) which perform simple textual entailment. To test our approach we develop a corpus based on the life cycle questions and showed that Our system achieves up to $18\%$ performance gain when compared to standard MCQ solvers.
中文速览
针对"生命周期"类科学选择题，现有机器学习问答系统因缺乏"序列中间位置""指示性特征"等背景知识而频频答错，而纯逻辑推理系统又要求把整段自然语言文本预先翻译成形式化语言，成本极高。本文提出了一种将回答集程序设计（Answer Set Programming, ASP）与外部自然语言推理模块相结合的方法：用ASP编写推理规则和背景知识，同时通过"生成-验证"函数对调用外部文本蕴含模型，让系统直接在原始自然语言文本上判断某个命题是否为真，从而绕开了繁琐的全文形式化翻译。研究者借助亚马逊众包平台构建了包含41篇生命周期文本、共5811道题目的新数据集，实验显示该系统相比标准选择题求解器最高提升18%的准确率。这项工作既证明了声明式推理可以直接作用于自然语言前提，也为需要外部背景知识的阅读理解任务提供了一条轻量级、可扩展的新路径。
原文 arXiv:1905.00198;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1905.00198v1