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

Knowledge base question-answering method fusing multi-loss function and attention mechanism

A loss function and knowledge base technology, applied in knowledge expression, text database query, electrical digital data processing, etc., can solve problems such as poor generalization, a large number of artificial rules, and low technical accuracy

Active Publication Date: 2020-05-08
BEIJING UNIV OF TECH
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem of low accuracy of existing knowledge base question answering technology and the need for a large number of artificial rules, the problem of poor generalization

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
  • Knowledge base question-answering method fusing multi-loss function and attention mechanism
  • Knowledge base question-answering method fusing multi-loss function and attention mechanism
  • Knowledge base question-answering method fusing multi-loss function and attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0047] Step S1, obtaining the entities in the question sentence.

[0048] Step S1.1, first process the training data set, use the knowledge base to label the data in the question sentence, and convert the entity recognition problem into a sequence labeling task for processing.

[0049] Step S1.2, use the existing sequence tagging network model, such as Bi-LSTM+CRF, to train the processed data set.

[0050] Step S1.3, mark the trained model on the test set, and mark the entities of the test set.

[0051] Step S1.4, for some entities, the marked entity in the question sentence is not exactly the same as the entity in the knowledge base, so the entity alias name table is used to process the entity in the question sentenc...

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 a knowledge base question-answering method fusing multiple loss functions and an attention mechanism. According to the method, questions and candidate answers are used as input, Bi-LSTM and Bi-GRU are used as main feature extractors, an attention mechanism is integrated, two loss functions are used for optimizing a model, model parameters are updated by calculating back propagation of loss values, and a network model is trained until the model converges; and finally, the questions and the candidate answers are mapped to a feature space with the same dimension through network training, the semantic similarity of the questions and the candidate answers is calculated by using the inner product between the feature vectors of the questions and the candidate answers, andthe difference between different answers is expanded by using the cosine similarity between the candidate answers. Through testing on a SimpleQuestions data set, the model has relatively strong feature mapping capability and relatively high accuracy, so that the superiority of the method is proved.

Description

technical field [0001] The invention relates to the field of deep learning, natural language processing, and knowledge base question answering, in particular to a knowledge base question answering method integrating multiple loss functions and an attention mechanism. Background technique [0002] Knowledge base question answering system can quickly and accurately answer questions raised by users, and its retrieval is more efficient than search engines, so it has recently become a new research hotspot in the field of natural processing. The process of knowledge base question answering is divided into several modules, among which the text matching of answers is a key step in knowledge base question answering. [0003] In the previous knowledge base question answering method, the professional knowledge of semantics is used to construct a semantic parser, which converts natural language questions into a logical form, and then converts this logical form into a corresponding datab...

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): G06F16/33G06F16/332G06F40/295G06F40/247G06N5/02
CPCG06F16/3329G06F16/3344G06N5/02
Inventor 杨新武张煜
Owner BEIJING UNIV OF TECH
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