Unlock instant, AI-driven research and patent intelligence for your innovation.

Word vector generation method, device and system

A technology of word vector and feature vector, applied in the field of language processing, can solve the problem of inaccurate word vector, achieve the effect of enhancing the ability of extraction and improving the degree of accuracy

Active Publication Date: 2020-03-27
ALIBABA GRP HLDG LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Embodiments of the present invention provide a method, device and system for generating word vectors to at least solve the technical problem of inaccurate word vectors generated in the prior art

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
  • Word vector generation method, device and system
  • Word vector generation method, device and system
  • Word vector generation method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] According to an embodiment of the present invention, an embodiment of a method for generating a word vector is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, Also, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0025] The method embodiment provided in Embodiment 1 of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. figure 1 A block diagram of a hardware structure of a computer terminal (or mobile device) for realizing a method for generating word vectors is shown. Such as figure 1 As shown, the computer terminal 10 (or mobile device 10) may include one or more (shown by 102a, 102b, ..., 102n in the figure) processor 102 (the processor 102 ma...

Embodiment 2

[0096] According to an embodiment of the present invention, a device for generating a word vector for implementing the above method for generating a word vector is also provided, Figure 7 It is a schematic diagram of a device for generating a word vector according to Embodiment 2 of the present application, such as Figure 7 As shown, the device 700 includes:

[0097] Obtaining module 702, configured to obtain at least one word in the sentence.

[0098] An extracting module 704, configured to extract stroke information of at least one stroke of the word.

[0099] The generating module 706 is configured to generate a stroke feature vector of the word based on the stroke information of the stroke, wherein the stroke feature vector represents local feature information of the word.

[0100] The determination module 708 is configured to determine the word vector of the word through the word vector generation model based on the stroke feature vector of the word, wherein the word ...

Embodiment 4

[0114] Embodiments of the present invention can provide a system for generating word vectors, including:

[0115] processor; and

[0116] The memory, connected to the processor, is used to provide instructions for the processor to process the following processing steps: acquire at least one word in the sentence; extract stroke information of at least one stroke of the word; stroke based on the stroke information, generating the stroke feature vector of the word, wherein the stroke feature vector represents the local feature information of the word; based on the stroke feature vector of the word, the word vector of the word is determined by the word vector generation model, Wherein, the word vector generation model is used to generate corresponding word vectors according to stroke feature vectors of words.

[0117] Further, the memory also provides instructions for the processor to process other steps in Embodiment 1, which will not be repeated here.

[0118] Example 4

[01...

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 word vector generation method, device and system. The method comprises the steps of obtaining at least one word in a statement; extracting stroke information of at least onestroke of the word; based on the stroke information of the strokes, generating stroke feature vectors of the words, wherein the stroke feature vectors represent local feature information of the words;based on the stroke feature vectors of the words, determining word vectors of the words through a word vector generation model, wherein the word vector generation model is used for generating corresponding word vectors according to the stroke feature vectors of the words. The technical problem that word vectors generated in the prior art are inaccurate is solved.

Description

technical field [0001] The present invention relates to the field of language processing, in particular, to a method, device and system for generating word vectors. Background technique [0002] It is difficult for computers to understand the semantics of human language. For example, "cat" and "cat" may be recognized by computers as two unrelated words, and it is difficult for computers to describe the semantic similarity between these two words. Therefore, when a computer processes language information, it needs to reflect the language information through data. The word vector technology just solves this problem. The word vector algorithm will generate a vector for "cat" and "cat", and then the computer can calculate the cosine of the angle between the vectors to calculate the semantic similarity of the two words ( A real number between 0-1), for example, if the similarity is 0.95, it means that "cat" and "cat" are two words with very close semantics. Therefore, the accur...

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): G06F40/284G06F40/289
Inventor 肖非曹绍升
Owner ALIBABA GRP HLDG LTD