Machine Translation
What is machine translation?
Translation of text from one language to another without human involvement. Also called automated translation "Translation performed by a computer".
Why?
Communication is our life.Without communication we can't express our feelings, share our thoughts.But there are about 6909 languages in the world and I don't think anyone in the world knows more than 10 languages.So to understand others' language machine translation is required which converts one language to another language with the use of software.It also helps in translating web content and web pages.
Types of Translation
1.Machine Translation
Sometimes the general meaning of a text is all you need from your translation. Machine translation provides the perfect combination of rapid, trusted and cost-effective translations when getting the general meaning across is sufficient.
2.Community Translation
Translating with community users provides accuracy for lower cost and reasonable speed. Community translation is less expensive, but may not provide the level of quality and consistency offered by professional translators. Use Community Translation for knowledge base articles, video subtitles, simple web pages, Wiki entries, and online newspapers.
3.Professional Translation
Professional translation offers the highest quality and includes additional levels of review to ensure accuracy. Use Professional Translation for very important content like press releases, brochures, and white papers, to name a few items.
Content Value Index
Types of machine translation system
- Rules Based Systems uses a combination of language and its grammatical rules.This system relies on many built-in linguistic rules and bilingual dictionaries for each language pair. The software parses text and creates a intermediate representation from which the text in the target language is generated. This process requires lexicons with syntactic,morphological and semantic information, and large sets of rules. But it is hard to handle exceptions to rules.
- Statistical systems: These systems does not depend on language rules instead they relies on existing multilingual corpora.They learn to translate by analysing large amount of data for each language pair.Building statistical translation models is a quick but minimum of 2 million words for a specific domain and even more for general language are required.Thats why these systems have high CPU and disk space requirements.
- Neural Machine Translation (NMT) is a new approach that makes machines learn to translate through one large neural network.In this a bidirectional recurrent neural network(RNN) is used which includes encoder to encode source sentence for second RNN, known as decoder which predict the words in target language.
The approach has become increasingly popular amongst MT researchers and developers, as trained NMT systems have started to show better translation performance in many language pairs compared to the phrase-based statistical approach.
*Google also uses NMT now named as Google Neural Machine Translation that uses artificial neural network.
References:
- https://leonardoaraujosantos.gitbooks.io/artificial-inteligence/content/recurrent_neural_networks/machine-translation-using-rnn.html
- https://en.wikipedia.org/wiki/Google_Neural_Machine_Translation
- https://en.wikipedia.org/wiki/Statistical_machine_translation
- https://en.wikipedia.org/wiki/Rule-based_machine_translation
- https://cs224d.stanford.edu/reports/GreensteinEric.pdf
- https://leonardoaraujosantos.gitbooks.io/artificial-inteligence/content/recurrent_neural_networks/machine-translation-using-rnn.html
Comments
Post a Comment