Cross-language text representation method and device

A text representation and cross-language technology, applied in the field of information processing, can solve problems such as difficulty in cross-language representation and poor representation effect, and achieve the effect of guaranteeing the representation effect

Active Publication Date: 2019-11-05
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF9 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] For this reason, the first purpose of the present invention is to propose a cross-language text representation method, which solves the technical problem in the prior art that cross-language processing models are difficult to overcome the barriers of different languages ​​and cause poor representation effects

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
  • Cross-language text representation method and device
  • Cross-language text representation method and device
  • Cross-language text representation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035]Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0036] The following describes the cross-language text representation method and device according to the embodiments of the present invention with reference to the accompanying drawings.

[0037] Aiming at the technical problem mentioned in the above background technology that the existing technology does not take into account the differences between languages ​​when performing cross-language text representation, resulting in inaccurate results based on cross-language text representation, the present invention proposes a method to ...

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 cross-language text representation method and device, and the method comprises the steps: obtaining a first training text and a first cross-language representation model corresponding to a first language, and enabling the first cross-language representation model to comprise a first universal vector sub-model and a text representation sub-model; obtaining a second trainingtext of a target language corresponding to the to-be-processed text; training a first universal vector sub-model according to the first training text and the second training text to obtain a second universal vector sub-model; and obtaining a second cross-language representation model of the target language according to the second universal vector sub-model and the text representation sub-model. Therefore, the universal vectors among different languages are mined based on semantic alignment processing, and cross-language text processing is performed based on the universal vectors, so that therepresentation effect of the cross-language processing model is ensured. The technical problem that in the prior art, a cross-language processing model difficultly crosses obstacles of different languages, and consequently the representation effect is poor is solved.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to a cross-language text representation method and device. Background technique [0002] Cross-language semantic representation technology, whose goal is to use a large amount of text in different languages ​​to learn, construct cross-semantic semantic representation, and assist cross-language text representation tasks with only a small amount of labeled data (such as machine translation, cross-language retrieval, question answering, reasoning, sentiment classification, etc.). [0003] related technologies, such as figure 1 As shown, cross-language semantic representation technology is divided into monolingual corpus and multilingual parallel corpus representation technology, wherein monolingual corpus refers to learning cross-language task models based on cross-language semantic representation (for example: cross-language language reasoning, reading comprehension, ...

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): G06F16/33G06F17/27G06K9/62
CPCG06F16/3344G06F18/214
Inventor 王硕寰孙宇
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