Open AccessVélþýðingar á íslensku og Apertium-þýðingarkerfið
Author(s) -
Ingibjörg Elsa Björnsdóttir
Publication year - 2016
Publication title -
orð og tunga
Language(s) - English
Resource type - Journals
eISSN - 2547-7218
pISSN - 1022-4610
DOI - 10.33112/ordogtunga.18.8
Subject(s) - machine translation , computer science , machine translation software usability , example based machine translation , natural language processing , computer assisted translation , icelandic , artificial intelligence , ambiguity , translation (biology) , rule based machine translation , vocabulary , linguistics , programming language , philosophy , chemistry , gene , biochemistry , messenger rna
There has been rapid development in language technology and machine translation in recent decades. There are three main types of machine translation: statistical ma-chine translation, rule-based machine translation, and example-based machine translation. In this article the Apertium machine translation system is discussed in particular. While Apertium was originally designed to translate between closely related languages, it can now handle languages that are much more different and variable in structure. Anyone can participate in the development of the Apertium system since it is an open source soft ware. Thus Apertium is one of the best options available in order to research and develop a machine translation system for Icelandic. The Apertium system has an easy-to-use interface, and it translates almost instantly from Icelandic into English or Swedish. However, the system still has certain limitations as regards vocabulary and ambiguity.