Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Question and answer matching method based on adaptive fusion multi-attention network

A matching method and attention technology, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., to achieve the effect of improving network performance

Pending Publication Date: 2021-06-15
SUN YAT SEN UNIV
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the technical defect that the present invention uses multiple self-attention networks to enhance the understanding of questions and answers through multiple rounds of processing, instead of obtaining multi-angle and multi-faceted information about questions and answers, the present invention provides a self-attention-based A Question and Answer Matching Method Adapted to Fused Multi-Attention Networks

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
  • Question and answer matching method based on adaptive fusion multi-attention network
  • Question and answer matching method based on adaptive fusion multi-attention network
  • Question and answer matching method based on adaptive fusion multi-attention network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] Such as figure 1 As shown, a question and answer matching method based on adaptive fusion multi-attention network, including the following steps:

[0054] S1: Convert each word in the question and answer into a word vector, and encode the word vector in the question and answer to obtain the word vector sequence of the question and answer;

[0055] S2: Use multiple self-attention networks to extract different aspects of information in a question according to the sequence of word vectors, and encode them into different question vectors; among them, a self-attention network extracts information in one aspect of a question, corresponding to a question vector ;

[0056] S3: Use a sequential attention network to generate a corresponding answer vector for each question vector;

[0057] S4: Calculate the matching score of each question vector and its corresponding answer vector, and adaptively fuse the matching score of multiple aspects of information by evaluating the weight...

Embodiment 2

[0059] More specifically, such as figure 2 As shown, in step S1, a bidirectional LSTM is used to encode the word vectors in the question and the answer respectively, so as to obtain a word vector representation that includes context information.

[0060] More specifically, given a sentence S=(w 1 ,w 2 ,...,w l ), use the bidirectional LSTM to encode the word vector to obtain the corresponding hidden layer:

[0061]

[0062]

[0063]

[0064] When the given sentence S is a question, the hidden layer vector sequence H of each word vector in the question is obtained q ={h q (1),...,h q (l)}, put H q ={h q (1),...,h q (l)} as the word vector sequence of the question;

[0065] When the given sentence S is the answer, the hidden layer vector sequence H of each word vector in the answer is obtained a ={h a (1),...,h a (l)}, put H a ={h a (1),...,h a (l)} as the word vector sequence of the answer;

[0066] Among them, w 1 ,w 2 ,...,w l are the l words in t...

Embodiment 3

[0096] In this embodiment, three public data sets cited by many papers are selected as the evaluation data sets, and the empirical research of the question and answer matching method based on adaptive fusion multi-attention network is carried out.

[0097] Table 1 is the situation of three public datasets.

[0098] Table 1

[0099] data set TrecQA WikiQA InsuranceQA Number of train / validation / test questions 1162 / 65 / 68 873 / 126 / 243 12887 / 1000 / 1800x2 average question length 8 6 7 average answer length 28 25 95 Average number of candidate answers 38 9 500

[0100] In order to make a fair comparison with previous studies, this example continues to use the previous evaluation criteria on the same data set. On TrecQA and WikiQA, this example uses MeanAveragePrecision (MAP) and MeanReciprocalRank (MRR) to evaluate the performance of the model. On the other hand, InsuranceQA follows the top1 correct rate used by predecessors, and it...

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 provides a question and answer matching method based on an adaptive fusion multi-attention network, and the method comprises the following steps: S1, converting each word in a question and an answer into a word vector, and coding the word vectors to obtain a word vector sequence; s2, extracting information of different aspects in a problem by using a plurality of self-attention networks, and respectively encoding the information into different problem vectors; s3, generating a corresponding answer vector for each question vector; and S4, calculating a matching degree score, adaptively fusing the matching degree scores of the information in multiple aspects, and carrying out question and answer matching according to the fused matching degree score. The invention provides a question and answer matching method based on an adaptive fusion multi-attention network, and solves the problem that a model using a plurality of self-attention networks at present enhances understanding of questions and answers through multi-round processing instead of obtaining multi-angle and multi-aspect information of the questions and answers.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, and more specifically, relates to a question and answer matching method based on an adaptive fusion multi-attention network. Background technique [0002] Deep learning has a strong function fitting ability, and using deep learning to perform answer selection tasks has the advantages of fast running speed, easy calculation, and better than traditional effects. By carefully designing the network structure and simulating the thinking process of people when choosing answers, it is expected that good results can be obtained. From previous studies, we know that the learning of question representation plays a very important role in answer selection. A good answer selection model should be able to generate high-quality question vectors and answer vectors, and fully capture the interactive relationship between questions and answers. In fact, it is difficult for a simple self...

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): G06F40/279G06K9/62G06N3/04G06N3/08
CPCG06F40/279G06N3/049G06N3/08G06N3/045G06F18/22G06F18/25
Inventor 杨猛梁伟日谷雨
Owner SUN YAT SEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com