Japanese verb identification method for machine translation

A recognition method and machine translation technology, which is applied to instruments, special data processing applications, and electronic digital data processing, etc., can solve the problems of morpheme information time-consuming, segmentation, and labor-consuming, so as to improve the effect of bilingual word alignment and machine translation. The effect of translation quality improvement

Active Publication Date: 2014-04-09
北京中献电子技术开发有限公司
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The original intention of this method is for OCR recognition. The purpose is to improve the correct recognition rate of OCR. After recognition, it does not need to be translated or otherwise processed. Its shortcoming is that it cannot completely segment a deformed word. In addition, the two dictionaries need to be processed separately, and extracting morpheme information is time-consuming and labor-intensive

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
  • Japanese verb identification method for machine translation
  • Japanese verb identification method for machine translation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0036] This specific embodiment describes the identification of all verbs in Japanese patent documents, and the conjugation forms of Japanese verbs involved include: basic form, past tense, passive form, causative form, perfect form, etc.

[0037] As shown in the figure, the Japanese verb recognition method of the present invention comprises the following steps:

[0038] Special vocabulary retrieval and labeling

[0039] Retrieve and mark special words according to the special vocabulary database we summarized, and do not participate in the subsequent recognition of Japanese verbs.

[0040] Now input Japanese as follows:

[0041] ①Certify スイッチがそのProjectとID (number)によってそれぞれ制御を行う.

[0042] ②気温が上がるのは, 阳の热が地を暖め, Groundが空気を暖めるからである.

[0043] The search results are as follows:

[0044] ①Authentication スイッチがそのProjectとID (number)によってそれぞれ+++adv控御を行う.

[0045] ②気温が上がる+++vことは, sunのhotがgroundをwarmめ, groundが空気をwarmめるからである.

[0046] "それぞれ" in sentence ① is a non-verb, because it cont...

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 discloses a Japanese verb identification method for machine translation and belongs to the field of natural language processing. The method has the advantages that the method is based on rules and combines with dictionaries by analyzing the conjugated form rules of Japanese verbs, the verbs in a text can be identified completely, and basic forms of the verbs can be obtained by form restoration; the method can use common universal dictionaries and is high in adaptability and robustness; by the method, the lexical analysis accuracy and bilingual word corresponding effect in machine translation are increased, and the translation quality of machine translation is increased as a whole.

Description

technical field [0001] The invention belongs to the field of natural language processing, and relates to an automatic recognition method of Japanese verbs, in particular to a machine translation-oriented Japanese verb recognition method based on the combination of rules and dictionaries. Background technique [0002] With the increasing frequency of technological and cultural exchanges between China and Japan, breaking through the barriers of understanding and conversion between languages ​​has become one of the key elements. Timely and accurate translation of Japanese information into readable and understandable Chinese information is not only theoretically important Value, more practical necessity and urgency. In the existing statistical machine translation system, word segmentation preprocessing is required before machine training on parallel corpora, and its quality will directly affect the translation quality. Due to the large number of inflected forms of Japanese verb...

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): G06F17/28
Inventor 张孝飞胡月卿马伟金善花孟翔李彦刚王强
Owner 北京中献电子技术开发有限公司
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
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