User:Eunsun041299/sandbox

History
Google Translation is a complimentary translation service developed by Google in April 2006. It translates multiple forms of texts and media such as words, phrases and webpages.

Originally Google Translate was released as a Statistical Machine Translation (SMT). Translating the required text into English before translating into the selected language was a mandatory step that it had to take. Since SMT uses predictive algorithms to translate text, it had poor grammatical accuracy. However, Google initially did not hire experts to resolve this limitation due to ever-evolving nature of language.

In January 2010, Google has introduced Android app and iOS version in February 2011 to serve as a portable personal interpreter. As of February 2010, it was integrated into browsers such as Chrome and was able to pronounce the text, automatically recognize words in the picture and spot unfamiliar text and languages.

In May 2014, Google acquired Word Lens to improve the quality of visual and voice translation. It is able to scan text or picture with one’s device and have it translated instantly. Moreover, the system automatically identifies foreign languages and translates speech without requiring individuals to tap the mic button whenever speech translation is needed.

In November 2016, Google has transitioned its translating method to a system called “Neural Machine Translation.” It uses Deep Learning techniques to translate the whole sentences at a time and ensures greater accuracy of the context.

As of 2018, it translates more than 100 billion words a day.

Functions
Google Translate can translate multiple forms of text and media, which includes text, speech, images, and videos. Specifically, its functions include:

Written Words Translation

 * A function that translates written words or text to a foreign language.

Website Translation

 * A function that translates a whole webpage to selected languages

Document Translation

 * A function that translates a document uploaded by the users to selected languages. The documents should be in the form of: .doc, .docx, .odf, .pdf, .ppt, .pptx, .ps, .rtf, .txt, .xls, .xlsx.

Speech Translation

 * A function that instantly translates spoken language into the selected foreign language.

Mobile App Translation

 * In 2018, Google Translate has introduced its new feature called “Tap to Translate,” which made instant translation accessible inside any apps without exiting or switching it.

Image Translation

 * A function that identifies text in a picture taken by the users and translates text on the screen instantly.

Handwritten Translation

 * A function that translates language that are hand written on the phone screen or drew on a virtual keyboard without the support of keyboard.

For most of its features, Google Translate provides the pronunciation, dictionary, and listen to translation. Additionally, Google Translate has introduced its own Translate app, so translation is available with mobile phone in offline mode.

Core Products
Google Translate offers two translation tools: Free Website Translation and Translate API

Free Website Translation
It is a feature that automatically translates the websites in foreign languages to one’s primary language.

Translate Application Programming Interface (API)
It is a paid offering that can be used to create software applications, websites or any tools that requires multilingual translation.

Limitations
Due to the differences in complexity and nature of language, the accuracy vary greatly among languages. Some produce better results than others. Typically, western languages such as English and Spanish are generally accurate, and the accuracy of African languages are often the poorest, followed by Asian and European languages.

After the Google Translate has deployed a new technology called “Neural Machine Translation,” to translate whole sentences or text block in the context at a time, seeing the alternative translation for a word or phrase is not available anymore. Moreover, in its “Written Words Translation” function, there is a word limit on the amount of text that can be translated at once. Therefore, long text should be transferred to a document form and translated through its “Document Translate” function.

Moreover, machine translation often does not identify the double meanings of a word. A word in foreign language might have two different meanings in the translated language. As a result, it might lead to mistranslations.

In addition, grammatical error remains as a major limitation that face Google Translate's attempts at accuracy.

Accuracy
Although Google Translate is not as reliable as Human Translation, it has sufficient ability to provide relatively accurate translation and a gist of foreign language text. It has ability to translate text with the general use of words and phrases in a consistent manner. A research conducted in 2011 showcased that Google Translate got slightly higher score than UCLA minimum score for English Proficiency Exam. Due to its use of identical choice of words without considering the flexibility of choosing the alternative words or expressions, it produces relatively similar translation to human translation from the perspective of formality, referential cohesion, and conceptual cohesion. Moreover, a number of languages are translated into the similar sentence structure and sentence length with the human translation. Google carried out a test that required native speakers of each language to rate the translation with a scale between 0 and 6 and the results showed that Google Translate got 5.43 on average.

Google Translate Community
Google constantly seeks for volunteers to be a part of its “Translate Community” to translate languages people speak and help improve Google Translate’s accuracy. There are two ways to contribute. First, Google will show a phrase then one should type in the translated version. Second, Google will show all possible translation for a phrase for individuals to click the right translation.

Statistical Machine Translation
Although, Google deployed a new system called “Neural Machine Translation” for better quality translation, there are languages that still use the traditional translation method called “Statistical Machine Translation.” It is a “rule-based” translation method that utilizes predictive algorithms to guess ways to translate texts in foreign languages. It aims to translate whole phrases rather than single words then gather overlapping phrases for translation. Moreover, it also analyzes bilingual text corpora to generate statistical model that translates texts from one language to another.

Neural Machine Translation
Google Translate deployed Neural Machine Translation in the late 2016 to produce high quality translation. Neural Machine Translation is a system that resembles how human brain translates languages. It uses Deep Learning techniques to learn more text and huge corpora of language segments such as words and phrases. Its text translation is based on already existing statistical model and it learns linguistic rules based on that statistical model by using algorithms. It creates faster and more accurate translation than Statistical Machine Translation.