A method and system for automatic answer summarization in a question answering system

Abstract

The invention provides an automatic answer summarizing method and system for a question answering system. The method comprises the following steps: obtaining a user query question and a candidate answer set returned by the question answering system; extracting a concept from the question and building mapping of the concept and the question to obtain a question-concept set; extracting the concept from a candidate answer sentence and building mapping of the concept and the sentence to obtain a sentence-concept set; taking a union set of the concept sets of all sentences to obtain an answer-concept set; carrying out concept expansion and concept reduction on the question-concept set to obtain a question-expand-concept set; taking the union set of the question-expand-concept set and the answer-concept set to obtain a hit-concept set; and carrying out sentence quality calculation on the concept included in the hit-concept set to obtain an answer summary. Weights of the sentences and the like are built by the relationship between the concepts in a concept network; the problem that the sentence can be irrelevant to the question is solved; and the sentence which is the most relevant to the question is selected out from the answer through an integer programming method to form the final answer summary.

Description

technical field [0001] The invention relates to the fields of computer information retrieval and natural language processing, in particular to an automatic answer summarization method and system based on concept network and integer programming, which are used in a question answering system. Background technique [0002] With the popularization of the Internet, more and more people seek help on the Internet. Faced with the ever-increasing mass of Internet knowledge, various question and answer systems headed by Baidu Zhizhi provide great convenience for them to seek information on the Internet. However, taking Baidu Zhizhi as an example, the answers are relatively short in length, and the noise such as colloquialism is relatively serious. As a result, the answers may contain incomplete information, or even not answer the question. Answer summarization technology is an effective technical means to solve the above problems. It aggregates and removes redundancy from the informat...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the problem of incomplete information and high noise in the results returned by the existing question answering system for user queries, the present invention provides an automatic answer summarization method used in the question answering system, which starts from the concept of questions and answers, Use the actual relationship of each concept in the concept network in the real world to construct sentences with equal weights to overcome the problem that sentences may have nothing to do with the question, and then use the method of integer programming to select the most relevant sentences in the answer to form the final answer Summary

Images