Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Text information processing method, model training method, and related devices

A text information and model technology, applied in the direction of electrical digital data processing, natural language data processing, character and pattern recognition, etc., can solve the problems of repeated segments and sentence barriers, and achieve the effect of avoiding sentence barriers

Active Publication Date: 2022-05-10
TENCENT TECH (SHENZHEN) CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the target sequences generated by the above-mentioned models often contain a large number of repetitive fragments and unreasonable sentences.

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 information processing method, model training method, and related devices
  • Text information processing method, model training method, and related devices
  • Text information processing method, model training method, and related devices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0082] The embodiment of the present application provides a text information processing method, a model training method, and related devices, which can ensure the replacement effect of Chinese error correction, and will not replace words with other words that are not related, avoiding the problem of unreasonable sentences Condition.

[0083] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and not necessarily Used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the application described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "corresponding to" and any variations thereof, are intended to cover a non-exclusive inclusion, for example, a p...

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

Embodiments of the present application provide a text information processing method, a model training method, and related devices. In the embodiment of the present application, the text sequence corresponding to the text information to be marked is calculated through the sequence labeling model. If there is a target element in the text sequence, it means that there is a wrong word in the text information to be marked, and the wrong word can also be called the first word , and then determine the second word corresponding to the target element, and finally replace the first word in the text information to be labeled with the second word, so that the replacement of wrong words can be realized. Moreover, the second word needs to be determined according to the associated thesaurus and the word to be replaced, so the embodiment of the present application can guarantee the replacement effect of the second word, and will not replace the first word with other words that are not related, avoiding the situation that the sentence does not make sense .

Description

technical field [0001] The embodiments of the present application relate to the field of artificial intelligence, and in particular, to a text information processing method, a model training method, and related devices. Background technique [0002] With the development of modern technology, online media and self-media are booming. These media publish a large number of articles with complex contents. How to automatically identify typos in articles and assist in judging the quality of articles is an important and time-consuming task. work. Compared with English, Chinese has rich and diverse expressions, flexible grammar and syntactic structure, and the causes of mistakes are also very different: there are superficial spelling mistakes, such as homophonic mistakes and similarity mistakes; there are also deep-level grammatical mistakes, such as misuse of prepositions and improper collocations , more difficult to capture proper name miswriting and logic errors, greatly increasi...

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 Patents(China)
IPC IPC(8): G06F40/117G06F40/232G06F40/279G06K9/62
CPCG06F18/214
Inventor 何蕾
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com