Semantic analysis method and device

A semantic analysis and semantic technology, applied in the field of semantic analysis methods and devices, can solve the problems of long model training time and low efficiency of semantic analysis

Active Publication Date: 2018-09-07
TENCENT TECH (SHENZHEN) CO LTD
View PDF5 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] For this reason, the present invention proposes a semantic analysis method to solve the te

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
  • Semantic analysis method and device
  • Semantic analysis method and device
  • Semantic analysis method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The following describes in detail the embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, and are intended to explain the present invention and should not be construed as limiting the present invention.

[0038] The semantic analysis method and device of the embodiments of the present invention are described below with reference to the accompanying drawings.

[0039] In artificial intelligence technology, in order to enable chatbots to accurately understand the user's semantics and achieve better human-computer interaction, it is usually necessary to use a large amount of training data to train the semantic representation of sentences based on the model.

[0040] In related technologies, ...

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 semantic analysis method and device. The method comprises the following steps of: for each sample sentence in a dialogue flow, inputting a word vector of each word in the sample sentence into an encoder model to obtain a sentence vector for expressing a semantic meaning of the sample sentence; respectively inputting the sentence vectors into a first decoder model corresponding to each context sentence of the sample sentence and a second decoder model corresponding to each word of the sample sentence so as to obtain a first identifier corresponding to the context sentence and a second identifier corresponding to the word; determining a value of a target function according probabilities of the first identifiers and probabilities of the second identifiers; carrying out parameter training on the encoder model according to the value of the target function; and inputting the word vector of each word in a test sentence into the trained encoder model so as to obtain asentence vector for expressing a semantic meaning of the test sentence. Through the method, the training time length can be shortened, the calculation efficiency can be improved, and the technical problems that the model training time is long and the semantic analysis efficiency is low in the prior art are solved.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to a semantic analysis method and device. Background technique [0002] In order to carry out better human-computer interaction, it is usually necessary to use a model to process the natural language input by the user to analyze the user's semantics. [0003] In the prior art, a recurrent neural network is usually used as the codec of the model to perform semantic analysis on the sentence to be analyzed. When training the model, since the encoder using the neural network must be calculated serially, when the length of the sentence received by the encoder is m (that is, contains m words), the calculation time of m time steps is required; at the same time, When the maximum length of the 2k context sentences of the sentence to be analyzed received by the decoder is n, since 2k decoders can be parallelized, but each decoder must be serialized, the calculatio...

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): G06F17/27G06F17/22
CPCG06F40/12G06F40/30G06N3/08G06N5/04G06N3/045G06F18/2148G06F17/16G06F18/2193
Inventor 鲁亚楠曹荣禹林芬
Owner TENCENT TECH (SHENZHEN) CO LTD
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