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

METHOD AND APPARATUS FOR GENERATING CONTEXT INFORMATION and Computer-readable recording medium

A technology for information generation and recording media, applied in computer parts, computing, computing models, etc., and can solve problems such as huge computational load

Pending Publication Date: 2020-04-21
FUJITSU LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method requires a huge amount of computation

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
  • METHOD AND APPARATUS FOR GENERATING CONTEXT INFORMATION and Computer-readable recording medium
  • METHOD AND APPARATUS FOR GENERATING CONTEXT INFORMATION and Computer-readable recording medium
  • METHOD AND APPARATUS FOR GENERATING CONTEXT INFORMATION and Computer-readable recording medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 approach

[0029] A first embodiment will be described.

[0030] figure 1 is a diagram for explaining an example of a context information generation device.

[0031] The context information generation device 10 of the first embodiment is designed to analyze documents written in natural language to facilitate natural language processing such as retrieval of similar sentences. The context information generation device 10 can be used for various natural language processing services including machine translation and dialog systems. The context information generation device 10 may be referred to as a computer or an information processing device. The context information generation device 10 may be a client device operated by a user, or a server device accessible via a network.

[0032] The context information generation device 10 includes a storage unit 11 and a processing unit 12 . The storage unit 11 may be a volatile semiconductor storage device such as a random access memory (RAM), or ...

no. 2 approach

[0048] A second embodiment will now be described.

[0049] The machine learning device 100 of the second embodiment is a natural language processing device that analyzes a document written in a natural language by machine learning using a neural network. The machine learning device 100 can find a sentence similar to a specific sentence based on the analysis result. The machine learning device 100 can be used for various services using natural language, such as machine translation, recommendation system, and Q&A system. The machine learning device 100 may be called a computer or an information processing device. The machine learning device 100 may be a client device used by a user, or a server device accessible through a network.

[0050] figure 2 is a block diagram illustrating an example of a hardware configuration of a machine learning device.

[0051] The machine learning apparatus 100 includes a CPU 101 , a RAM 102 , an HDD 103 , a video signal processing unit 104 , a...

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 method and an apparatus for generating context information and a computer-readable recording medium. A memory stores therein a document and a plurality of word vectors that are word embeddings respectively computed for a plurality of words. A processor extracts, with respect to one of the words, two or more surrounding words within a prescribed range from one occurrence position where the one word occurs, from the document, and computes a sum vector by adding word vectors corresponding to the surrounding words. The processor determines a parameter such as to predict the surrounding words from the sum vector and the parameter using a machine learning model. The processor stores the parameter as context information for the one occurrence position, in association withthe word vector corresponding to the one word.

Description

technical field [0001] Embodiments discussed herein relate to a context information generating method, a context information generating device, and a computer-readable recording medium. Background technique [0002] In the field of natural language processing that processes documents written in natural language, word embedding vectors can be used as feature information representing features of words. Word embeddings capture the meaning (definition) of words and provide a way to associate similarity vectors with words with similar meanings. The use of word embedding vectors enables the efficient search for sentences similar to query sentences, which in turn enables the provision of various natural language processing services including machine translation and dialogue systems. [0003] For example, word embedding vectors are generated as follows. For each word in the training document, surrounding words that appear near the word are extracted from the training document, and...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/284G06N20/00G06N3/08G06V30/40
CPCG06N20/00G06N3/08G06F40/232G06F40/56G06F40/30G06N3/088G06V30/40G06V30/274G06V10/82G06N3/044G06F40/274G06V30/414G06V30/416
Inventor 大仓清司片冈正弘尾上聪
Owner FUJITSU LTD
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com