Method and device for parsing question sentences in knowledge base

Abstract

An embodiment of the present invention provides a method for analyzing questions in a knowledge base, including: receiving a question input by a user; performing phrase detection on the question to determine a candidate phrase; mapping the candidate phrase to a resource item in the knowledge base; further determining the observation Predicate values ​​and possible question parsing spaces. For each proposition set in the possible question analysis space, perform uncertainty reasoning to calculate the confidence degree according to the value of the observed predicate and the implicit predicate, and obtain the combination of true propositions in the proposition set whose confidence meets the preset conditions; According to the combination of the true propositions, a formalized query statement is generated. The embodiments of the present invention use observation predicates and implicit predicates to perform uncertainty reasoning, and can convert natural language questions into formalized query sentences. Moreover, the method of uncertainty reasoning can be applied to knowledge bases in any domain, and has domain scalability, so that there is no need to manually configure conversion rules for knowledge bases.

Description

technical field [0001] Embodiments of the present invention relate to the communication field, and more specifically, relate to a method and device for analyzing questions in a knowledge base. Background technique [0002] Knowledge base (Knowledge Base, KB) is a structured, easy-to-operate, easy-to-use, comprehensively organized knowledge cluster in knowledge engineering. A collection of interconnected pieces of knowledge stored, organized, managed, and used in computer memory by way of representation. [0003] At present, a large number of knowledge resources and knowledge communities have emerged on the Internet, such as Wikipedia, Baidu Encyclopedia, and Hudong Baike. From these knowledge resources, existing research has excavated a large-scale knowledge base centered on entities and entity relationships. In addition, there are some domain knowledge bases, such as weather knowledge base, catering knowledge base, etc. [0004] The construction of the knowledge base has...

AI Technical Summary

Problems solved by technology

However, in the current question answering system, the conversion rules are manually configured, which not only consumes a lot of manpower, but also has poor domain scalability.

Images