Intelligent question-answering oriented sentence pair semantic matching method based on semantic feature map

A semantic feature and semantic matching technology, applied in semantic analysis, neural learning methods, natural language data processing, etc., can solve the problems of lack of one-dimensional convolution semantic information, sentence semantic information coding processing cannot be ignored, and interactive information cannot be captured.

Pending Publication Date: 2020-11-27
QILU UNIV OF TECH
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since natural language sentences themselves belong to one-dimensional information, when applying convolutional neural networks, existing work usually only uses one-dimensional convolution kernels
Although the one-dimensional convolutional neural network can capture local information more effectively, it can only process sentences in one dimension, and cannot capture the interactive information between di

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent question-answering oriented sentence pair semantic matching method based on semantic feature map
  • Intelligent question-answering oriented sentence pair semantic matching method based on semantic feature map
  • Intelligent question-answering oriented sentence pair semantic matching method based on semantic feature map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0111] as attached Figure 8 As shown, the main framework structure of the present invention includes a multi-granularity embedding module, a deep semantic feature map construction network module, a feature transformation network module and a label prediction module. Among them, the multi-granularity embedding module performs embedding operations on the input sentences at word granularity and word granularity, and passes the results to the deep semantic feature map construction network module of the model. The deep semantic feature map construction network module contains several layers of encoding structures, such as Figure 7 As shown, the first-layer encoding structure encodes the word embedding representation and the word embedding representation output by the multi-granularity embedding module respectively to obtain the first-layer word encoding result and the first-layer word encoding result; the first-level word encoding result After being processed by reshape, the fir...

Embodiment 2

[0117] as attached figure 1 As shown, the sentence-to-semantic matching method based on the semantic feature map for intelligent question-answering of the present invention, the specific steps are as follows:

[0118] S1. Construct a sentence pair semantic matching knowledge base, as attached figure 2 As shown, the specific steps are as follows:

[0119] S101. Downloading datasets on the network to obtain original data: downloading datasets that have been published on the network for semantic matching of sentence pairs or artificially constructed datasets, and using them as raw data for constructing a knowledge base for semantic matching of sentence pairs.

[0120] Example: There are many public sentence-pair semantic matching data sets for intelligent question answering systems on the Internet, such as the LCQMC data set [Xin Liu, Qingcai Chen, Chong Deng, Huajun Zeng, Jing Chen, Dongfang Li, and Buzhou Tang.Lcqmc:A large-scale chinese question matching corpus, COLING2018...

Embodiment 3

[0239] as attached Figure 6 As shown, the sentence pair semantic matching device based on the intelligent question answering based on the semantic feature map of embodiment 2, the device includes,

[0240] The sentence-pair semantic matching knowledge base construction unit is used to obtain a large amount of sentence-pair data, and then preprocess it to obtain a sentence-pair semantic matching knowledge base that meets the training requirements; the sentence-pair semantic matching knowledge base construction unit includes,

[0241] The sentence-pair data acquisition unit is responsible for downloading the sentence-pair semantic matching datasets that have been published on the network or artificially constructed datasets, and using them as the original data for constructing the sentence-pair semantic matching knowledge base;

[0242] The original data hyphenation preprocessing or word segmentation preprocessing unit is responsible for preprocessing the raw data used to const...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an intelligent question and answer oriented sentence pair semantic matching method based on a semantic feature map, and belongs to the technical field of artificial intelligence and natural language processing. The technical problem to be solved by the invention is how to capture more semantic context features, the relationship of coded information between different dimensions and the interaction information between sentences, and intelligent semantic matching of sentence pairs is realized. The adopted technical scheme is as follows: a sentence pair semantic matching model consisting of a multi-granularity embedding module, a deep semantic feature map construction network module, a feature conversion network module and a label prediction module is constructed and trained; and deep semantic feature graph representation of sentence information and two-dimensional convolutional encoding representation of semantic features are realized, and meanwhile, a final matching tensor of sentence pairs is generated through two-dimensional maximum pooling and attention mechanisms, and the matching degree of the sentence pairs is judged, so that the purpose of intelligent semantic matching of the sentence pairs is achieved. The device comprises a sentence pair semantic matching knowledge base construction unit, a training data set generation unit, a sentence pair semantic matching model construction unit and a sentence pair semantic matching model training unit.

Description

technical field [0001] The invention relates to the technical fields of artificial intelligence and natural language processing, in particular to a sentence-pair semantic matching method based on a semantic feature map for intelligent question-answering. Background technique [0002] The intelligent question answering system is one of the core technologies of human-computer interaction. It can automatically find matching standard questions in the question and answer knowledge base for the questions raised by users, and push the answers to the standard questions to users, which can greatly reduce the burden of manual answers. . Intelligent question answering system has a wide range of practical applications in self-service, intelligent customer service and other fields. For the vastly different questions raised by users, how to find matching standard questions for them is the core technology of the intelligent question answering system. The essence of this technology is to ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F16/33G06F16/332G06F40/289G06F40/30G06N3/04G06N3/08
CPCG06F16/3344G06F16/3329G06F40/30G06F40/289G06N3/08G06N3/045
Inventor 鹿文鹏于瑞张旭
Owner QILU UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap