Skip to main content

Machine Translation

                         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

  1. 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. 
  2. 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.
  3. 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

Popular posts from this blog

NLP in Video Games

From the last few decades, NLP (Natural Language Processing) has obtained a high level of success in the field  of Computer Science, Artificial Intelligence and Computational Logistics. NLP can also be used in video games, in fact, it is very interesting to use NLP in video games, as we can see games like Serious Games includes Communication aspects. In video games, the communication includes linguistic information that is passed either through spoken content or written content. Now the question is why and where can we use NLP in video games?  There are some games that are related to pedagogy or teaching (Serious Games). So, NLP can be used in these games to achieve these objectives in the real sense. In other games, one can use the speech control using NLP so that the player can play the game by concentrating only on visuals rather on I/O. These things at last increases the realism of the game. Hence, this is the reason for using NLP in games.  We ...
4 comments
Read more

Discourse Analysis

NLP makes machine to understand human language but we are facing issues like word ambiguity, sarcastic sentiments analysis and many more. One of the issue is to predict correctly relation between words like " Patrick went to the club on last Friday. He met Richard ." Here, ' He' refers to 'Patrick'. This kind of issue makes Discourse analysis one of the important applications of Natural Language Processing. What is Discourse Analysis ? The word discourse in linguistic terms means language in use. Discourse analysis may be defined as the process of performing text or language analysis, which involves text interpretation and knowing the social interactions. Discourse analysis may involve dealing with morphemes, n-grams, tenses, verbal aspects, page layouts, and so on. It is often used to refer to the analysis of conversations or verbal discourse. It is useful for performing tasks, like A naphora Resolution (AR) , Named Entity Recognition (NE...
5 comments
Read more

Semantic Similarity using Word Embeddings and Wordnet

Measuring semantic similarity between documents has varied applications in NLP and  Artificial sentences such as in chatbots, voicebots, communication in different languages etc. . It refers to quantifying similarity of sentences based on their literal meaning rather than only syntactic structure.  A semantic net such as WordNet and Word Embeddings such as Google’s Word2Vec, DocToVec can be used to compute semantic similarity. Let us see how. Word Embeddings Word embeddings are vector representations of words. A word embedding tries to map a word to a numerical vector representation using a dictionary of words, i.e. words and phrases from the vocabulary are mapped to the vector space and represented using real numbers. The closeness of vector representations of 2 words in the real space is a measure of similarity between them. Word embeddings can be broadly classified into frequency based (eg: count vector, tfidf, co occurrence etc) and prediction based (eg: Contin...
Post a Comment
Read more