Method for extracting event sentence pattern from Chinese sentence

A technology of sentences and events, which is applied in the field of extracting event sentence patterns in Chinese sentences, can solve the problems of immaturity and reduction in analysis, and achieve the effect of overcoming immaturity and reducing requirements

Active Publication Date: 2011-01-05
CERTUS NETWORK TECHNANJING
View PDF2 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, this method does not need to do a complete syntactic analysis, which reduces the requirements for the syntactic analyzer, can overcome the current

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 for extracting event sentence pattern from Chinese sentence
  • Method for extracting event sentence pattern from Chinese sentence
  • Method for extracting event sentence pattern from Chinese sentence

Examples

Experimental program
Comparison scheme
Effect test

specific example

[0242] The lower syntactic block sequence is: [P-vp eat / v-@][O-np rice / n-@]of / uJDE[H-np bowl / n-@].

[0243] This string of syntactic blocks can be combined to form a large object block [O-np eat / v rice / n's / uJDE bowl / n-@].

[0244] So the fusion rule is:

[0245] P O u J DE H → O 4 0.85.

[0246] It can be seen that the length of this rule is 4 (including the function word "uJDE" in the middle of the block), and the reliability is 0.85, that is, if there are 100 function block sequences in the format of "P O uJDE H", 85 of them are Sequences are merged into "O".

[0247] (4) System initialization

[0248] (4.1) Set data structure

[0249] Set the following data structures: word Verb, syntax block Block, each input sentence EveryRecord, all input sentences vector input, rule table vector for syntactic block fusion rules, where:

[0250] I. word Verb, information such as word and its part of speech in the reservation sentence, forms following format: {}, wherein:

[02...

Embodiment

[0459] The event sentence pattern extraction method that the present invention proposes needs to complete the following steps successively:

[0460] (1) Data preparation

[0461] Data preparation is to complete three parts of operations, one is to call the part-of-speech mapping and extension module to convert the part-of-speech of each word in the input sentence into an extended TCT part-of-speech tag; the other is to call the syntax block analysis module to Sentences are analyzed as syntactic blocks; the third is to call the event knowledge base retrieval module, and use the target verb information and meaning item information in the input to obtain the complete meaning item description of the verb and the corresponding relationship between general roles and special roles in the verb frame.

[0462] The following example illustrates preprocessing:

[0463] Enter a sentence:

[0464] Ministry of Finance / n , / , Ministry of Agriculture / n , / , Ministry of Chemical In...

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 for extracting an event sentence pattern from a Chinese sentence. The method comprises the following steps of: initializing by a computer, wherein the initialization of the computer comprises steps of defining relative terms, loading a data file, setting a data structure and loading a basic processing module; taking information initialized by the computer as input data; extracting the event sentence pattern according to the input information; acquiring event blocks according to the event sentence pattern; acquiring a universal role labeling result of each event block; and acquiring the role labeling result special for each event block according to the universal role labeling result. By the method of the invention, a heuristic rule can be flexibly utilized, the entire processing process can conform to the characteristics of a language per se, meanwhile the method does not need complete syntactic parsing, and the requirements on a syntactic parser are reduced, so that various conventional parsing tools can be conveniently utilized, and Chinese shallow semantic parsing is realized.

Description

technical field [0001] The invention relates to the application field of natural language processing, in particular to a method for extracting event sentence patterns in Chinese sentences. Background technique [0002] Semantic Role Labeling, also known as Shallow Semantic Parsing, is an exploration of the semantic understanding of natural language sentences. It mainly labels the semantic roles of components related to target predicates in sentences. [0003] The semantic role labeling process usually has four stages: 1) filtering, usually using some simple heuristic rules to filter out those labeling units (syntactic components, phrases, etc.) that cannot become semantic roles in the syntactic analysis results; 2) semantic Role recognition, identifying which labeling units are arguments of a target verb; 3) Semantic role classification, labeling semantic roles for labeling units determined to be target verb arguments; 4) Post-processing, using some heuristic rules to label ...

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
Inventor 周强陈丽欧
Owner CERTUS NETWORK TECHNANJING
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