Classification retrieval-based automatic question and answer method and system

Abstract

The invention discloses a classification retrieval-based automatic question and answer method and system. The method comprises the steps of firstly performing Chinese natural language processing on ashort-answer question to generate a syntax tree, and then according to key verbs and conjunctions in a question sentence, splitting the complex question sentence containing multiple sub-questions intosimple question sentences having more definite semantics and only containing single questions; secondly classifying the simple question sentences by using triggering words corresponding to predefinedquestion sentence types, extracting key information required by question sentence templates of the types from the question sentences, and correspondingly filling template slots to form question sentence templates containing all information required for question answering; thirdly according to the types of the question sentence templates, retrieving keywords in a corresponding template knowledge base according to the key information in the template slots to obtain multiple candidate answers; and finally, selecting optimal answers from the candidate answers as answers of the simple question, and then integrating the answers of all the simple question to obtain a final answer.

Description

technical field [0001] The invention belongs to the field of computer technology, and relates to natural language processing and automatic question-and-answer technology. Question and answer method. Background technique [0002] Natural language processing (natural language processing) is a sub-discipline in the field of artificial intelligence and linguistics. It studies various theories and methods that can realize effective communication between humans and computers using natural language. The key to processing natural language is to allow computers to "understand" natural language so that computers can interact with humans. The key technologies of natural language processing include Chinese word segmentation, part-of-speech tagging, syntactic analysis, named entity recognition, reference resolution, dependency analysis, etc. [0003] Question answering system (question answering system), based on information retrieval technology and natural language processing, can aut...

AI Technical Summary

Problems solved by technology

[0005] The problem to be solved by the present invention is: how to automatically answer middle school geography short-answer questions in specific fields, questions that are relatively complex, questions that can be classified, and questions that have corresponding retrieval methods for different categories through the set knowledge base

Images