Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Bilingual dictionary construction method and device

A technology for bilingual dictionaries and construction methods, applied in neural learning methods, neural architectures, natural language translation, etc., can solve the problems of consuming a lot of manpower and time

Active Publication Date: 2017-11-03
TSINGHUA UNIV
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing technologies for automatically building bilingual dictionaries generally rely on a seed bilingual dictionary, which still requires cross-lingual resources
However, building a seed bilingual dictionary requires a lot of manpower and time

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
  • Bilingual dictionary construction method and device
  • Bilingual dictionary construction method and device
  • Bilingual dictionary construction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be described below in conjunction with an exemplary communication system.

[0024] The invention discloses a method for constructing a bilingual dictionary, comprising the steps of:

[0025] S101. Input monolingual corpus A of language a (also referred to as source language) and input monolingual corpus B of language b (also referred to as target language), respectively represent the words in monolingual corpus A and monolingual corpus B is the word vector;

[0026] S102, training to obtain the mapping relationship between the word vector of the monolingual corpus A and the word vector of the monolingual corpus B;

[0027] S103 , constructing a bilingual dictionary according to the mapping relationship.

[0028] In S101, words or phrases in the corpus are converted into word vectors through word2vec, and the dimension of the word vector is the same as that of the generator used for training the mapping relationship. The discriminator is use...

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 bilingual dictionary construction method and device, which are used for solving the problem of how to automatically construct a bilingual dictionary without depending on a seed bilingual dictionary. The bilingual dictionary construction method comprises the steps of S101, inputting a monolingual corpus A of a language a, inputting a monolingual corpus B of a language b, and representing words in the monolingual corpus A and words in the monolingual corpus B as word vectors; S102, performing training to obtain a mapping relationship between the word vectors of the monolingual corpus A and the word vectors of the monolingual corpus B; and S103, constructing the bilingual dictionary according to the mapping relationship. According to the method and the device, a neural network model consisting of a generator and a discriminator is built from the monolingual word vectors obtained by training the monolingual corpora; and by designing a proper loss function and training technology, the mapping relationship between the word vectors of the two languages is directly obtained, and the bilingual dictionary is constructed, so that the bilingual dictionary can be finished without depending on the seed bilingual dictionary.

Description

technical field [0001] The invention relates to computer corpus processing technology, in particular to a bilingual dictionary building method and device. Background technique [0002] With the progress of globalization, international exchanges are becoming more and more frequent, and people begin to need translations in more and more languages. However, for many small languages, not only is there a shortage of translators, but the performance of automatic machine translation is also poor. At this time, bilingual dictionaries are particularly important, which can not only be used directly by humans, but also help improve the effect of machine translation. [0003] For small languages ​​with few language resources, the most abundant language resources are monolingual corpus. Therefore, it would be most practical to use this kind of corpus to automatically build a bilingual dictionary. However, the existing technologies for automatically constructing bilingual dictionaries ...

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): G06F17/28G06F17/27G06N3/04G06N3/08
CPCG06N3/08G06F40/247G06F40/42G06N3/045
Inventor 孙茂松张檬刘洋栾焕博
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com