Method for adding punctuation marks to punctuation-free text

A punctuation mark and punctuation technology, applied in instruments, biological neural network models, calculations, etc., can solve problems such as inability to obtain better symbol addition effects, low prediction accuracy of symbol labels, and inability to extract text sequences well, etc., to achieve Excellent memory ability, avoid manual labor, increase the effect of part of speech and semantic features

Inactive Publication Date: 2018-12-04
EAST CHINA NORMAL UNIV
View PDF3 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these two methods cannot extract the features of the text sequence very well, so the prediction accuracy of the symbol label corresponding to the text sequence is low, and a good symbol addition effect cannot be achieved.

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
  • Method for adding punctuation marks to punctuation-free text
  • Method for adding punctuation marks to punctuation-free text
  • Method for adding punctuation marks to punctuation-free text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0026] The invention provides a method for adding punctuation marks to non-punctuation text, and adds punctuation to non-punctuation text after speech recognition, see figure 1 . Through this process, as long as the relevant language sequence data set is prepared in advance, the parallel corpus can be automatically obtained and the model training can be completed. The model obtained through training can complete the addition of punctuation marks to a sentence or a paragraph of articles without punctuation.

[0027] The present invention can support different languages ​​such as Chinese, English, German, etc., and can be applied to any application scene that needs to add punctuation in speech recognition, speech translation, intell...

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 method for adding punctuation marks to a punctuation-free text. The method comprises the steps of processing to obtain a parallel corpus, training the parallel corpus througha neural network framework to obtain a symbol adding model, and then adding corresponding punctuations to a text to be processed by using the symbol adding model. According to the method, the addition of the punctuation marks can be realized simply and conveniently, and the accuracy and wide applicability of the punctuation marks can be improved.

Description

technical field [0001] The invention relates to the fields of natural language processing (NLP) and information processing, and in particular to a method for adding symbols to a recognized text sequence without punctuation after speech recognition. Background technique [0002] In modern society, Automatic Speech Recognition (ASR) system has been paid more and more attention and applied. ASR can be applied to various fields and environments, such as voice assistants, intelligent customer service and voice translation, etc. However, the current ASR system can only generate text sequences without punctuation marks, which makes it difficult to understand the sentences without punctuation marks generated after long speech recognition, which will cause serious ambiguity problems, so that they cannot be analyzed and used. . In some usage scenarios of voice assistants, intelligent customer service and voice translation, the sequence of pure text brings huge reading pressure and e...

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): G06F17/27G06N3/04
CPCG06F40/284G06N3/045
Inventor 杨燕战蕾贺樑
Owner EAST CHINA NORMAL UNIV
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