Word sense disambiguation method and system

A word meaning disambiguation and word meaning technology, applied in the field of word meaning understanding and word meaning disambiguation methods and systems, to achieve the effect of improving accuracy

Inactive Publication Date: 2010-09-22
NEC (CHINA) CO LTD
View PDF4 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The present invention aims to solve many problems exist...

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 sense disambiguation method and system
  • Word sense disambiguation method and system
  • Word sense disambiguation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] image 3 is a structural block diagram showing a word sense disambiguation system 300 according to an embodiment of the present invention. Such as figure 1 In contrast to the system 100 shown, the system 300 may also be composed of two parts, namely, a concept context-based word sense disambiguation component and a storage component. Such as image 3 As shown, as the core of the present invention, the conceptual context-based word meaning disambiguation component includes a vocabulary input device 301 , a conceptual context extraction device 302 , a conceptual context-based word meaning scoring device 303 and a word meaning selection device 304 . In cooperation with the work of the word sense disambiguation component, the storage component includes a plurality of storage devices 305-309.

[0024] Figure 4 is showing image 3 A flowchart of the working process of the system 300 is shown. The process 400 starts at step 401, wherein the vocabulary input device 301 c...

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 word sense disambiguation method and system. In the method, semantic information contained in a body or a classification system with a hierarchical structure is used for carrying out semantic disambiguation on a target word. The method comprises the following steps of: inputting a target word w with various word senses (w1, w2 to wn); extracting the concept of the target word from the related body and a concept context in the body; grading the various word senses of the target word based on the concept context; and selecting a proper word sense of the target word according to a grading result. According to the invention, because various related semantic features in the context (the concept context) of the target word are considered, the accuracy rate of the word sense disambiguation is obviously improved.

Description

technical field [0001] The present invention generally relates to natural language processing, and more specifically, to a method and system for word sense understanding and word sense disambiguation. Background technique [0002] The so-called word sense disambiguation is to determine the meaning of polysemous words in a specific context, which has a wide range of applications in natural language processing, information retrieval, information extraction, ontology integration and other fields. [0003] The current word sense disambiguation methods are all aimed at the target vocabulary in the text or sentence. Generally speaking, the text context of the target vocabulary constitutes a feature space for distinguishing word meanings, which may specifically include adjacent words of the target vocabulary, fixed collocations, or other grammatical features obtained from sentence structure analysis. [0004] Existing word sense disambiguation methods mainly use grammatical featur...

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): G06F17/27G06F17/30
Inventor 李建强赵彧刘博
Owner NEC (CHINA) 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