Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Machine translation-based construction method for Chinese semantic knowledge base

A technology of semantic knowledge base and construction method, applied in the field of Chinese semantic knowledge base construction, can solve the problems of lack of Chinese semantic knowledge base, expensive manpower and time, etc.

Active Publication Date: 2016-06-15
黑龙江省工研院资产经营管理有限公司
View PDF5 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to solve the problem of lack of Chinese semantic knowledge base, the problem of expensive manpower and time in the prior art, and the problem of improving the performance of semantic knowledge base translation based on cross-language mapping, and propose a machine translation based The construction method of the Chinese semantic knowledge base

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
  • Machine translation-based construction method for Chinese semantic knowledge base
  • Machine translation-based construction method for Chinese semantic knowledge base
  • Machine translation-based construction method for Chinese semantic knowledge base

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0025] Specific embodiment 1: The method for constructing a Chinese semantic knowledge base based on machine translation in this embodiment is specifically prepared according to the following steps:

[0026] Based on the entities in the source language semantic knowledge base, the source language-side monolingual corpus is segmented and named entity recognition, and the machine translation model based on the source language-side semantic knowledge base graph structure information;

[0027] Step 1. Use the entities in the source language semantic knowledge base to identify the source language corpus in the original bilingual corpus to obtain the source language corpus labeled with the entity;

[0028] Step 2: Use the source language corpus with the entities obtained in Step 1 to construct a topic model, and calculate the topic distribution of the entity according to the topic model;

[0029] Step 3: The source language corpus with the entity annotated and the target language corpus with...

specific Embodiment approach 2

[0038] Specific embodiment two: This embodiment is different from specific embodiment one in that: when the source language corpus is preprocessed, the original corpus will be preprocessed such as word segmentation; although the current word segmentation technology can achieve word segmentation very well, However, because many vocabularies are new words, the word segmentation technology is still insufficient; the named entity recognition technology is also encountering similar problems; however, for the present invention, since the source language side semantic knowledge base is known, therefore

[0039] Step 1: Use the source-language-side semantic knowledge base to construct a source-language-side entity vocabulary, where the source-language-side entity vocabulary includes the names of all entities in the source-language-side semantic knowledge base (the entity is generally a specific person and one One word in kind);

[0040] Step 12: Add the source language-end entity vocabular...

specific Embodiment approach 3

[0041] Specific embodiment three: this embodiment is different from specific embodiment one or two in that: in step two, the source language corpus with the entity marked in step one is used to construct a topic model, and the specific topic distribution of the entity is calculated according to the topic model process:

[0042] Step two: Use the source language corpus with entities obtained in step one to train the topic model to obtain the word-topic distribution:

[0043]

[0044] Where s i Represents the words in the source language corpus where the entity is annotated, i∈{1,2....,V s }, V s Is the size of the vocabulary in the source language corpus where the entity is annotated; z k Is the k-th topic, k∈{1,2,...,K}, K is the total number of topics;

[0045] Step two, use the word-topic distribution obtained in step two to obtain the topic distribution of each entity:

[0046] Other steps and parameters are the same as those in the first or second embodiment.

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 relates to a construction method for a Chinese semantic knowledge base, in particular to a machine translation-based construction method for a Chinese semantic knowledge base.The problems that Chinese semantic knowledge bases are insufficient and the labor cost and the time cost are high in the prior art are solved, and the performance of semantic knowledge base translation based on cross-language mapping is improved.The method comprises the steps that 1, a source language end corpus annotated with the entity is obtained; 2, the subject distribution of the entity is obtained through calculation according to a subject model; 3, the translation probability of the entity in the source language end semantic knowledge base is extracted from a phrase translation table according to a source language end entity word list and marked as a P (tj|si); 4, an entity translation model based on source language end semantic knowledge base graph structure information is built.The construction method is applied in the field of construction of Chinese semantic knowledge bases.

Description

Technical field [0001] The invention relates to a method for constructing a Chinese semantic knowledge base, in particular to a method for constructing a Chinese semantic knowledge base based on machine translation. Background technique [0002] The knowledge base brings together a series of concepts, examples, and relationships, and is used more and more widely in the field of natural language processing, such as automatic question and answer, event detection, and understanding user queries. At present, the more famous knowledge bases include WordNet, HowNet, FrameNet, YAGO, Freebase, DBpedia, etc., which have played a very good role in search, question and answer, etc. respectively. The knowledge base is mainly divided into two types according to the construction method. One is the knowledge base constructed manually by relying on the basic knowledge of linguistics and linguistic experts, such as WordNet, HowNet, etc.; the other is automatically constructed based on large-scale...

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): G06F17/30G06F17/27G06F17/28
CPCG06F16/367G06F40/295G06F40/44G06F2216/01
Inventor 曹海龙李晓倩赵铁军杨沐昀徐冰
Owner 黑龙江省工研院资产经营管理有限公司
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
Eureka Blog
Learn More
PatSnap group products