Multi-feature fusion neural machine translation error detection method based on data enhancement training

A multi-feature fusion and machine translation technology, applied in natural language translation, instruments, computer parts, etc., can solve problems such as waste of manpower, inability to meet translation needs, and low efficiency

Pending Publication Date: 2021-06-08
UNIV OF SCI & TECH OF CHINA
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0022] However, the above-mentioned existing translation error detection schemes have problems such as low efficien

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
  • Multi-feature fusion neural machine translation error detection method based on data enhancement training
  • Multi-feature fusion neural machine translation error detection method based on data enhancement training
  • Multi-feature fusion neural machine translation error detection method based on data enhancement training

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

[0033] In the application of machine translation, the existing error detection scheme of translation results is a feasible way to use manual error detection, but the existing scheme relies too much on manual intervention, and needs to summarize the types of errors and collect a large number of corpora, which is inefficient. To this end, the embodiment of the present invention provides a multi-feature fusion neural machine translation error detection method...

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 multi-feature fusion neural machine translation error detection method based on data enhancement training, which is used for artificially classifying and concluding real error sentences, counterfeiting a large amount of data through a data enhancement method, and enhancing the effect and robustness of a machine translation error detection model. In addition, source text and translation length ratio information and translation language model PPL score feature information are added into model input, so that the classification accuracy of the error detection model is further improved, and based on the error detection scheme, the detection result can be used for subsequent error correction and can also be used for error prompt, and translation user experience is provided; the invention can also be used for evaluation indexes of machine translation effects.

Description

technical field [0001] The invention relates to the technical field of machine translation error detection, in particular to a multi-feature fusion neural machine translation error detection method based on data augmentation training. Background technique [0002] Machine translation, also known as automatic translation, refers to the process of using computers to convert one natural language (source language) into another natural language (target language). Machine translation has important practical value. [0003] The machine translation effect of the current neural network framework has been significantly improved, for example: 1) Devlin J, Chang M W, Lee K, et al.BERT: Pre-training of Deep Bidirectional Transformers for LanguageUnderstanding[J].2018; 2) Bahdanau D, Cho K, Bengio Y. Neural Machine Translation by Jointly Learning to Align and Translate [J]. Computer ence, 2014; 3) Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, and Yann N. Dauphin. Convolution...

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): G06F40/58G06K9/62
CPCG06F40/58G06F18/214G06F18/253
Inventor 陈贝多黄青青杜俊
Owner UNIV OF SCI & TECH OF CHINA
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