A method and system for improving the accuracy of knowledge base question answering

Abstract

The present invention proposes a method and system for improving the accuracy of knowledge base questions and answers, including: obtaining user questions to be answered, extracting subject entities in the user questions, using the subject entities to search the knowledge base, and obtaining each candidate The path information of the answer is used as the candidate path, and the user question is preprocessed to obtain the vector representation of the user question; the vector representation is used to score each step relationship on the candidate path using the attention mechanism, and the candidate path is obtained. The relationship confidence of each step of the relationship, and sum all the relationship confidences on the candidate path to obtain the path confidence of the relationship path; sort all the candidate paths according to their confidence path confidence, and output the path with the highest confidence The candidate path is used as the answer result of the user question. The invention strengthens the role of the intermediate node in the whole relationship inference and improves the accuracy of the relationship inference.

Description

technical field [0001] The invention relates to the field of Internet technology and the field of relationship inference in big data analysis, and in particular to a knowledge base question answering method and system for relationship inference based on path information. Background technique [0002] The knowledge base question answering system is a research hotspot in the field of natural language processing. The user inputs a complete and colloquial question sentence, and the system can return a clear answer string by querying in the structured knowledge base. Knowledge in a knowledge base is usually stored in the form of triples, ie (head entity, relation, tail entity). Generally speaking, a knowledge base question answering system consists of two core modules, namely, a topic entity inference module and a relation inference module. The topic entity inference is to find out the entities that the user is interested in in the user's question and link them to the correspond...

AI Technical Summary

Problems solved by technology

The method based on semantic analysis often requires a large amount of manually labeled data because it needs to learn how to construct structured query statements. This type of labeled data requires labelers to be familiar with the corresponding linguistic knowledge, which is expensive

The embedding-based method ignores the relationship inference step, treats single-relationship questions and multi-relationship questions uniformly, regards all nodes within two hops connected to the subject entity in the knowledge base as candidate answers, and does not explicitly model multi-relationship questions The final impact of intermediate nodes on relationship inference. This method of encoding all nodes as encoded candidate answers is similar to information retrieval. When dealing with multi-relational problems, it does not make full use of the information in the question and knowledge base, making the result of relationship inference relatively vague

Images