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

Machine translation evaluation method and equipment and machine translation method and equipment

A technology of machine translation and evaluation methods, applied in the field of machine translation, can solve problems such as affecting the reliability of evaluation, and achieve the effect of improving performance and improving translation results.

Inactive Publication Date: 2017-05-31
NTT DOCOMO INC
View PDF8 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method requires two translation models from the source language to the target language and from the target language back to the source language, and the performance of back translation from the target language to the source language will also affect the reliability of the evaluation

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 evaluation method and equipment and machine translation method and equipment
  • Machine translation evaluation method and equipment and machine translation method and equipment
  • Machine translation evaluation method and equipment and machine translation method and equipment

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0021]

example 2

[0023]

[0024] Semantic roles are divided into core semantic roles and additional semantic roles. The core semantic role is represented by ARG+number, which is generally considered to include 5 categories, among which ARG0 represents the doer of the action, ARG1 represents the recipient of the action, ARG2 represents the tool, means, etc. of the action, ARG3 represents the starting point, and ARG4 represents the end point. The additional semantic role is denoted by AGRM-, which is used to indicate the time, place, etc. of the action, such as "in 1989" in Example 1 above.

[0025] As mentioned earlier, the inventors realized that semantic roles can express semantics to a certain extent, and bilingual parallel sentence pairs are mutual translations, so they should be equivalent in semantics, which is reflected in the semantic role Labeling, two corresponding sentences should have a consistent predicate-argument structure. For example, the following example shows the argumen...

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 machine translation evaluation method and equipment and a machine translation method and equipment which are used for a cross-language question and answer system. The machine translation evaluation method comprises the steps that semantic role labeling is conducted on source language query sentences and corresponding target language query sentences obtained through machine translation; the alignment probability of each labeled argument in the source language query sentences and each labeled argument in the target language query sentences is calculated; the translation quality of the target language query sentences is determined on the basis of all the calculated alignment probabilities. According to the method, a novel machine translation evaluation scheme which utilizes semantic role labeling and is based on the argument alignment probabilities is provided; by means of the method, accurate machine translation evaluation can be provided, and then the performance of the cross-language question and answer system is improved.

Description

technical field [0001] The present disclosure generally relates to machine translation, and specifically relates to a machine translation evaluation method and device for a cross-language question answering system, and a machine translation method and device. Background technique [0002] Cross-language question answering system (Cross-language question answering system) is the product of the use of cross-language information retrieval technology in automatic question answering systems. Compared with single-language automatic question answering systems, cross-language question answering systems need to involve more complex cross-language and information Retrieval and other processing techniques. It requires the system to receive the user's question expressed in the source language as input, the system automatically finds the best answer to the question in another language's corpus, and returns the answer to the user in the source language. Since the language of the question...

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): G06F17/28
Inventor 王晓利张永生
Owner NTT DOCOMO INC
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

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