Translation method and translation device based on neural network model

A neural network model and neural network technology, applied in the field of translation methods and devices based on the neural network model, can solve the problems of serious missing words, short translation results, inability to add or enrich features, etc., to achieve appropriate length and reduce missing words efficiency, and the effect of improving accuracy

Active Publication Date: 2015-11-18
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF5 Cites 55 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Usually, the RNN translation model can only use a limited number of word vocabulary (usually less than 30,000 words), resulting in words outside the vocabulary (Out-of-vocabulary, OOV) cannot be translated
[0006] 2. The RNN translation model only supports bilingual sentence pairs for training, and it is difficult to use the target language monolingual corpus that can effect

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
  • Translation method and translation device based on neural network model
  • Translation method and translation device based on neural network model
  • Translation method and translation device based on neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] figure 1 It is a flowchart showing a translation method based on a neural network model in the first embodiment of the present invention. The method can be executed on the device described in the second embodiment.

[0035] Reference figure 1 , In step S110, the source language sentence is obtained.

[0036] According to an exemplary embodiment of the present invention, step S110 includes one of the following processes:

[0037] Receive text data and use the text data as a sentence in the source language.

[0038] Receive voice data, perform voice recognition on the voice data to obtain voice-recognized text data, and use the voice-recognized text data as a sentence in the source language.

[0039] Receive picture data, perform OCR on the picture data to obtain text data recognized by OCR, and use the text data recognized by OCR as a sentence in the source language.

[0040] In step S120, the source language sentence is encoded to obtain a vector sequence.

[0041] Specifically, t...

Embodiment 2

[0069] Figure 4 It is a logical block diagram showing a translation device based on a neural network model in the second embodiment of the present invention. Can be used to perform as figure 1 The method steps of the illustrated embodiment.

[0070] Reference Figure 4 The translation device based on the neural network model includes a sentence acquisition module 410, a sentence encoding module 420, a candidate word prediction module 430, and a sentence generation module 440.

[0071] The sentence acquisition module 410 is used to acquire sentences in the source language.

[0072] Further, the sentence acquisition module 410 may include one of the following units:

[0073] The text data receiving unit (not shown) is used to receive text data and use the text data as a sentence in the source language.

[0074] The voice data receiving and recognition unit (not shown) is used to receive voice data, perform voice recognition on the voice data to obtain voice-recognized text data, and 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 embodiment of the invention provides a translation method and a translation device based on a neural network model, wherein the translation method based on the neural network model comprises the following steps: obtaining a statement of a source language; coding the statement of the source language to obtain a vector sequence; predicting corresponding candidate words in a target language word by word based on the vector sequence; and generating a statement of the target language according to the candidate words obtained by prediction. The translation method and the translation device based on the neural network model in the embodiment of the invention are capable of performing translation in combination with a variety of translation characteristics; and thus, the translation quality, the fluency and the readability of a translation result are improved.

Description

Technical field [0001] The present invention relates to the technical field of machine translation, in particular to a translation method and device based on a neural network model. Background technique [0002] In recent years, Recurrent Neural Network (RNN) technology has been widely used in the field of machine translation. Compared with traditional statistical machine translation systems, machine translation systems based on recurrent neural networks can make full use of global semantic information, and the translation quality is significantly improved. [0003] However, machine translation technology based on recurrent neural networks also has obvious shortcomings: [0004] 1. The vocabulary is restricted. [0005] Generally, the RNN translation model can only use a limited number of word vocabularies (usually within 30,000 words), resulting in out-of-vocabulary (OOV) words that cannot be translated. [0006] 2. The RNN translation model only supports bilingual sentence pairs for...

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): G06F17/28G06N3/02
Inventor 何中军和为吴华王海峰
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) 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