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

A lexical semantic predicting method and device

A prediction method and vocabulary technology, applied in special data processing applications, instruments, electrical and digital data processing, etc., can solve problems such as deviation, time-consuming and laborious

Inactive Publication Date: 2018-12-11
TSINGHUA UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the time-consuming and labor-intensive and biased problems of the existing manual labeling method for sememes, or at least partially solve the above problems, the present invention provides a sememe prediction method and device

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
  • A lexical semantic predicting method and device
  • A lexical semantic predicting method and device
  • A lexical semantic predicting method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0023] In one embodiment of the present invention, a method for predicting lexical sememes is provided, figure 1 It is a schematic diagram of the overall flow of the vocabulary sememe prediction method provided by the embodiment of the present invention, the method includes: S101, for any preset position in the vocabulary to be predicted, if the character at the preset position in each vocabulary sample is the same as the character in the vocabulary to be predicted The characters in the preset positions are the same, and the elements corresponding to each vocabulary sample are obtained from the preset sememe vocabulary matrix; wherein, the rows of the sememe vocabulary mat...

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 lexical semantic predicting method and device. The method comprises the following steps: for any preset part of a vocabulary to be predicted, if the characters of the preset part in each vocabulary sample are the same as the characters of the preset part in the vocabulary to be predicted, obtaining the elements corresponding to each of the vocabulary samples from the preset semantic vocabulary matrix; obtaining a first score of each character whose meaning originally belongs to each preset part in the vocabulary to be predicted according to an element corresponding toeach vocabulary sample, and obtaining a second score of each character whose meaning originally belongs to each preset part in the vocabulary to be predicted according to the first score of each character whose meaning originally belongs to each preset part in the vocabulary to be predicted; according to the second score of each of the meanings originally belonging to the vocabulary to be predicted, determining the semantics of the vocabulary to be predicted. The invention improves the labeling efficiency and the accuracy of predicting the lexical semantics.

Description

technical field [0001] The invention belongs to the technical field of natural language analysis, and more specifically relates to a method and device for predicting a vocabulary sememe. Background technique [0002] Sentences are composed of words, and different words have similarities and differences. HowNet is a widely used artificial annotation database, which is used to describe the semantics of different words. It marks words as a structure composed of a series of sememes, and sememes are smaller and indivisible semantic sets than words. It has a more basic meaning than vocabulary. For example, the meanings of blacksmiths include person, position, metal, and worker. From these meanings, we can know that blacksmiths are a kind of people. This kind of people is a kind of occupation, related to metals, and belongs to the industrial field. HowNet and its labeled sememe information can be used in natural language processing tasks such as word disambiguation, sentiment ana...

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): G06F17/27
CPCG06F40/284G06F40/289
Inventor 刘知远金晖明朱昊谢若冰孙茂松林芬林乐宇
Owner TSINGHUA UNIV