Text translation method and device, equipment and storage medium

A text and translation model technology, applied in the field of text translation, can solve problems such as difficulty in ensuring the consistency and fluency of text translation

Active Publication Date: 2019-04-02
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF8 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the above invention, the inventor found that the prior art has the following defects: splitting the entire t...

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
  • Text translation method and device, equipment and storage medium
  • Text translation method and device, equipment and storage medium
  • Text translation method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] figure 1 It is a flow chart of a text translation method provided by Embodiment 1 of the present invention. The method of this embodiment can be executed by a text translation device, which can be implemented by means of hardware and / or software, and can generally be integrated into a device. For example server. The method of this embodiment specifically includes:

[0028] S110. Obtain the original language text.

[0029] In this embodiment, the original language text may specifically be any language text. Further, the original language text can be acquired through direct input from the user, or through scanning and image-to-text conversion, or through speech recognition. This implementation The example does not limit this.

[0030] S120. Use the text translation model to translate the original language text to obtain the target language text corresponding to the original language text, wherein the text translation model is a translation model obtained after correct...

Embodiment 2

[0037] figure 2 It is a flowchart of a text translation method provided by Embodiment 2 of the present invention. This embodiment is optimized on the basis of the above-mentioned embodiments. In this embodiment, a specific text evaluation result is given, model correction steps are added, and specific methods for obtaining the best probability translation and random probability translation are given. implementation.

[0038] Correspondingly, the method in this embodiment specifically includes:

[0039] S210. Obtain the best probability translation of the original translation model for the test text, and the random probability translation.

[0040] In this embodiment, the steps of correcting the translation model, ie step 210 to step 230, are added. Further, in this embodiment, the text evaluation results of the training translation are specifically the text evaluation results of the best probability translation and the text evaluation results of the random probability tran...

Embodiment 3

[0051] Figure 3a It is a flowchart of a text translation method provided by Embodiment 3 of the present invention. This embodiment is optimized on the basis of the above-mentioned embodiments. In this embodiment, an overall evaluation algorithm for the specific translation results is given as the teacher motivation algorithm and a method for obtaining text evaluation results corresponding to the specific teacher motivation algorithm. A method for modifying the model and a specific implementation of the structure of the materialized text translation model.

[0052] Correspondingly, the method in this embodiment specifically includes:

[0053] S310. Obtain the best probability translation of the original translation model for the test text, and the random probability translation.

[0054] S320. Obtain the first vector corresponding to the best probability translation and the second vector corresponding to the standard translation of the test text according to the RNN obtained...

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 embodiment of the invention discloses a text translation method and device, equipment and a storage medium. The method comprises the steps of obtaining an original language text; translating the original language text by using a text translation model; obtaining a target language text corresponding to the original language text, wherein the text translation model is a translation model obtained by correcting an original translation model according to a text evaluation result of a training translation, the training translation model is an output result after translation of the original translation model, and the text evaluation result is used for evaluating the semantic relationship of the context text in the training translation. According to the technical scheme provided by the embodiment of the invention, the problem that in the prior art, semantic consistency before and after translation of a translated text obtained by independently translating each sentence is poor is solved;according to the technical scheme, the text translation model is effectively corrected, the translation accuracy of the text translation model is improved, and then the front-back semantic consistencyand fluency of translated texts are improved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of text translation, and in particular, to a text translation method and device, equipment, and storage medium. Background technique [0002] With the increasing global international cooperation, more and more textual information needs to be translated into languages ​​of different countries, such as e-commerce websites, media information, literary publications, etc. It is unrealistic to rely solely on manual translation, so more and more translation companies and related companies use machine translation to compile information. [0003] Translation models in the prior art, such as neural machine translation, are basically based on sentence-level translation and optimization. Specifically, the text to be translated is generally split into multiple sentences, and then the split sentences are translated separately, and finally the translation results of the split sentences are connec...

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): G06F17/27G06F17/28
CPCG06F40/51G06F40/30G06F40/58G06N3/08G06N3/044G06N3/045
Inventor 熊皓何中军李芝忻舟王海峰
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
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