Method and device for determining semantic matching degree

Abstract

The present invention provides a method and device for determining semantic matching degree. The method includes: acquiring the first sentence and the second sentence; dividing the first sentence and the second sentence into x and y sentence segments respectively; The word vector in each sentence segment is convolved with the word vector in each sentence segment of the second sentence to obtain a three-dimensional tensor; the adjacent vectors in the x row y column one-dimensional vectors are synthesized and / or screened , until the three-dimensional tensor is combined into a one-dimensional target vector; according to the target vector, the semantic matching degree between the first sentence and the second sentence is determined. In the embodiment of the present invention, according to the word order, the sentences to be matched are divided into sentence segments with the word vector as the unit, and the two sentence segments in the two sentences are convoluted to obtain a three-dimensional tensor, which contains each The local matching information of sentence fragments between sentences, the semantic matching result obtained based on this three-dimensional tensor is more accurate.

Description

technical field [0001] The present invention relates to the field of semantic matching, and more specifically, to a method and device for determining the degree of semantic matching. Background technique [0002] Semantic matching technology has become one of the core technologies of natural language processing, and has played an important role in many commercial systems, for example, voice assistants (such as Siri, Google Now), machine translation (Machine Translation), and chat robots (such as Microsoft Xiaobing) and so on. [0003] In the prior art, each sentence to be matched is usually decomposed into multiple word vectors, and each word vector has a fixed dimension. On this basis, the sentence to be matched is represented by the linear superposition of the word vectors it contains. The degree of semantic matching of two sentences is described as the inner product between the vectors representing the two sentences. [0004] Although the above semantic matching method...

AI Technical Summary

Problems solved by technology

This method of overall statement matching expresses all the information of the statement through a vector, often ignoring the impact of the matching degree of local segments between sentences on the final semantic matching result, resulting in inaccurate matching results

Images