Analyzing the impact of deep learning algorithms and fuzzy logic approach for remote English translation

A remote English translation is used for assisting with on-demand support for adaptable sentence conversion and language understanding. The problem with on-demand translations is the precision verification of the words used. This article addresses the precision problem by assimilating deep learning...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Scientific reports Ročník 14; číslo 1; s. 14556 - 15
Hlavní autor: Han, Xiuying
Médium: Journal Article
Jazyk:angličtina
Vydáno: London Nature Publishing Group UK 24.06.2024
Nature Publishing Group
Nature Portfolio
Témata:
639/166
639/705
Adaptability
Algorithms
Deep learning
English translation
Fuzzy algorithm
Fuzzy logic
Humanities and Social Sciences
multidisciplinary
Precision improvement
Science
Science (multidisciplinary)
Translation
Translations
Deep learning
Fuzzy algorithm
Precision improvement
English translation
ISSN:2045-2322, 2045-2322
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:A remote English translation is used for assisting with on-demand support for adaptable sentence conversion and language understanding. The problem with on-demand translations is the precision verification of the words used. This article addresses the precision problem by assimilating deep learning and fuzzy decision algorithm for remote translation support. The method named Fusion-dependent Precision Translation Approach (FPTA) conducts a series of recurrent validations on word usage and sentence completion for the given inputs. First, the completed sentences are verified using the understandability and meaning intended using deep learning in two recurrent layers. The first layer is responsible for identifying word placement and understandability and the second is responsible for meaning verification. The recurrent training is tuned using a fuzzy decision algorithm by selecting the maximum best-afford solution. The constraint’s understandability and meaning are augmented for tuning the outputs by preventing errors consequently. In precise, the error sequences are identified from the first layer for fuzzification across various inputs. This process improves the word adaptability from different languages reducing errors (12.49%) and improves the understandability (11.57%) for various translated sentences.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-024-64831-w