Intelligent dialogue system response method based on tree kernel computing and intelligent dialogue system

Abstract

The invention provides an intelligent dialogue system response method based on tree kernel computing and an intelligent dialogue system. The response method comprises the following steps: training Chinese words to obtain a word vector table; acquiring a question sentence A1 input by a user, and selecting one question sentence as A2 by the system in sequence; inputting A1 and A2 into a word segmentation tool to obtain sentence word sets C1 and C2; inputting C1 and C2 into a syntactic analyzer to obtain a syntactic tree T1T2; trimming the T1 and the T2; inputting the trimmed T1 and T2 into a tree kernel calculation model to obtain similarity scores of the T1 and T2; calculating to obtain similarity scores of A1 and A2 according to the similarity scores of T1 and T2; recording similarity scores of A1 and A2, and judging whether another question sentence exists or not as A2; and selecting the question sentence with the maximum similarity with the A1, and outputting the answer corresponding to the question sentence as a result. Compared with the prior art, the tree kernel computing-based intelligent dialogue system response method and the intelligent dialogue system are higher in accuracy.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to an intelligent dialogue system answering method based on tree core calculation and the intelligent dialogue system. Background technique [0002] The calculation of text semantic similarity is one of the basic tasks in natural language processing tasks, and plays an important role in many application scenarios such as machine translation, intelligent dialogue, and search engines. [0003] In most of the current studies, the main goal of text semantic similarity calculation is to give an appropriate scoring model close to human judgment to calculate the similarity between texts. According to different input data, the calculation of text semantic similarity is divided into word level, sentence level, short text level and long text level. The similarity between a pair of sentences is generally measured by a similarity score, and the score ranges from 0 to 5. 0 means that ...

AI Technical Summary

Problems solved by technology

[0009] However, most tree kernel structure comparison methods usually only use string hard matching to compare the similarity of the tree structure, and these simple judgments will lead to the loss of semantic information

There are also some studies using soft matching methods to compare the similarity of sentences, such as using LSA for semantic annotation, but these methods are judged by stacking some semantic features, which not only require a lot of additional resources to generate features, but also lack short text expression ability

Images