A SYSTEMATIC READING IN STATISTICAL TRANSLATION: FROM THE STATISTICAL MACHINE TRANSLATION TO THE NEURAL TRANSLATION MODELS

Achieving high accuracy in automatic translation tasks has been one of the challenging goals for researchers in the area of machine translation since decades. Thus, the eagerness of exploring new possible ways to improve machine translation was always the matter for researchers in the field. Automat...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of ICT Ročník 16; číslo 2; s. 408
Hlavní autori: El Maazouzi, Zakaria, El Mohajir, Badr Eddine, Al Achhab, Mohammed
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Kedah Darul Aman Universiti Utara Malaysia 01.12.2017
UUM Press
Predmet:
Machine translation
Natural language processing
neural language model
Neural networks
recurrent neural networks
ISSN:1675-414X, 2180-3862
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Achieving high accuracy in automatic translation tasks has been one of the challenging goals for researchers in the area of machine translation since decades. Thus, the eagerness of exploring new possible ways to improve machine translation was always the matter for researchers in the field. Automatic translation as a key application in the natural language processing domain has developed many approaches, namely statistical machine translation and recently neural machine translation that improved largely the translation quality especially for Latin languages. They have even made it possible for the translation of some language pairs to approach human translation quality. In this paper, we present a survey of the state of the art of statistical translation, where we describe the different existing methodologies, and we overview the recent research studies while pointing out the main strengths and limitations of the different approaches.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1675-414X
2180-3862
DOI:10.32890/jict2017.16.2.11