Google Translate

The translator of Google (from the English Google Translate) is a multilingual system of automatic translation, developed and provided by Google, to translate text, voice, images or video in real time from one language to another. It offers web interface, as well as mobile interfaces for iOS and Android, and an API, which developers can use to build browser extensions, applications, and other softwares. The Google Translator has the ability to translate 103 languages at different levels, the system provides a free service and is used daily by more than 200 million people.

Google incorporated its neuronal machine translation system in November 2016, a system that according to the company will improve the dynamic evolution of the Translator, since it will analyze the composition of the sentences taking into account a series of factors. The system learns over time and user queries, which improves the quality of its translations. For now, Google has incorporated the English, French, German, Portuguese, Spanish, Chinese, Japanese, and Turkish languages into this system.

Since December 2016, free text translation has been limited by Google to 5,000 characters, while web page translation has no extension limit.

Web interface

For some languages, the Google Translator can pronounce the translated text, highlight words and phrases that correspond to the source and the target text, and act as a simple dictionary for one word at a time. If "Detect language" or "Text in an unknown language" is selected, the system can automatically identify the language.

In the web interface, users can suggest alternative translations, such as for technical terms, or correct errors, and these suggestions will be included in future updates of the translation process. If a user enters a URL in the original text, the Google Translator will produce a hyperlink to an automatic translation of the website. For some languages, text can be entered using: an on-screen keyboard, a handwriting tablet using handwriting recognition algorithms, or a microphone using a voice recognition system.

Integration with the browser

The Google Translator is available in some browsers as an extension that translates the texts it collects on the websites accessed.

The system has a series of Firefox extensions for Google Translator, which allows you to select translation service commands are also available several Google Gadgets that use Google Translate to integrate with iGoogle and other Web pages.

There is also an extension for the Google Chrome browser, in February 2010, the Google Translator was integrated into the standard Google Chrome browser to automatically translate the web page that is consulted.

Mobile device interface

The application supports 90 languages and allows you to translate: 37 languages based on a photo of the source text, 32 languages based on voice in conversation mode and 27 languages based on a real-time video in augmented reality mode.

Conversation Mode is a Google Translator interface that allows users to communicate fluidly with a person in another language. The interface is available for some languages only.

The 'input from camera' functionality allows users to take a picture of a document or sign and Google Translate recognizes the text of the image using optical character recognition (ROC) technology and translates into the selected target language. Camera input mode is not available for all languages.

The application has the ability to translate text in real time using the camera of the mobile device, using the Google Word Lens application. The speed and quality of the real-time characteristic video translation (augmented reality) were further enhanced by the use of convolutional neural networks.

Android version

The Google Translator is available as a free download application for users of the Android operating system. It works simply as the browser version, Google Translate for Android contains two main options: "SMS Translation" and "History".

The application supports 90 languages and the voice input has the capacity to process 15 languages. It is available for devices with Android 2.1 and higher and can be downloaded by searching for "Google Translator" on Google Play. The application has the functionality, by which any language can be translated by simply focusing the text on the camera of the mobile device and also offers a conversation mode that uses Google's voice command and cloud storage to translate the dialogue between two people who speak different languages.

IOS version

There is a Google HTML5 Translator web application for iOS for iPhone, iPod Touch and iOS users. The current Google Translator application is compatible with iPhone, iPad and iPod Touch updated for iOS 7.0 or higher. It accepts voice input in 15 languages and allows the translation of a word or phrase in one of the more than 50 languages available. The system has the option of providing the translated version of the text by speaking it out loud in 23 different languages.

API

In May 2011, Google announced that the Google Translator API for software developers had become obsolete and would cease to function on December 1, 2011, "due to the high operating cost resulting from abuse in its use". Because the API is used in numerous third party websites, this decision led some developers to criticize Google and question the viability of using Google APIs in their products. In response to public pressure, Google announced in June 2011 that the API would still be available through a paid service.

Translation Methodology

The Google Translator does not use grammar rules, since its algorithms are based on statistical analysis instead of analysis based on traditional grammar rules. The original creator of the system, Franz Josef Och, has criticized the effectiveness of rule-based algorithms highlighting the best performance of systems based on statistical approaches. The Google Translator is based on a method called translation Automatic statistics, specifically on the results of research conducted by Och with whom he won the contest DARPA for speed machine translation in 2003. Och was head of the group of automatic translation of Google to leave the company to join the company Human Longevity in July 2014.

In its internal operation, Google Translate does not translate directly from one language to another (I1 → I2). Instead, it often translates first from the source language to English and then from English to the target language (I1 → EN → I2). However, because the English, and the like all human language is ambiguous and depends on the context, this method can cause translation errors. For example, the translation of vous from French to Russian gives vous → you → ты or Bы/вы. If Google used an unambiguous, artificial language as an intermediary, it would be vous → you → Bы/вы or you → thou → ты.

When Google Translate translates, it searches for patterns in hundreds of millions of documents to decide which is the best translation. By detecting patterns in documents that were translated by humans, the system makes intelligent decisions about the most appropriate translation.

The following languages do not have a direct Google translation to or from English. These languages are translated by the intermediate language indicated (which in any case is closely related to the desired language, but is more widely spoken), then pass through the English (in a process comprising three successive translations):

• Belarusian (be ↔ ru ↔ in ↔ other),
• Catalan (ca ↔ is ↔ in ↔ other),
• Haitian Creole (ht ↔ fr ↔ in ↔ other),
• Galician (gl ↔ pt ↔ in ↔ other),
• Slovak (sk ↔ cs ↔ in ↔ other),
• Ukrainian (uk ↔ ru ↔ in ↔ other),
• Urdu (ur ↔ hi ↔ in ↔ other).

According to Och, a solid basis for the development of a usable statistical automatic translation system for a new language pair requires having a bilingual text corpus (or a parallel collection) of more than 150 to 200 million words, and two corpus monolingual each one of more than one billion words. It is then possible to use models statistics from these data translate between these languages.

To acquire this enormous amount of linguistic data, Google uses for example United Nations documents and reports. The UN normally publishes its documents and records in the six official languages of the UN, which has produced a large corpus of text in 6 languages.

Google representatives have participated in the national conferences in Japan, where Google has requested bilingual data from researchers.

When the Google Translator generates a translation, it searches for patterns in hundreds of millions of documents to help decide on the best translation. By detecting patterns in documents that have already been translated by human translators, Google Translate makes intelligent guesses (using an artificial intelligence system) as to what a proper translation should be.

Prior to October 2007, for languages other than Arabic, Chinese and Russian, Google Translate used SYSTRAN, a translation software engine that was used by several other online translation services such as Babel Fish (now discontinued). But since October 2007, Google Translate uses proprietary proprietary technology based on statistical machine translation.

Limitations

The Google translator has its limitations. The free service limits the number of paragraphs and the range of technical terms that can be translated, and although it can help the reader understand the general content of a text in another language, it does not always deliver precise translations, and sometimes it is repeated literally The same word you want to translate. The Google translator tries to differentiate between imperfect and perfect times in Romanesque languages so that habitual and continuous acts in the past often become individual historical events. Although seemingly pedantic, this may lead to incorrect results that would have been avoided by a human translator. The knowledge of the subjunctive modeIt is practically non-existent. On the other hand, the second informal person (you) is often chosen, whatever the context or use accepted. If your English reference material contains only "you" forms, it becomes difficult for you to translate into a language that has more forms.

Some languages produce better results than others. The Google Translator does a correct job especially when English is the target language and the source language is one of the languages of the European Union due to the large number of documents translated by the EU Parliament, to which it has Access the system. An analysis conducted in 2010 concluded that the translation from French to English is relatively accurate, and analyzes conducted in 2011 and 2012 showed that the translation from Italian to English is also accurate. However, if the source text is short, rule-based machine translations often perform better. This effect is particularly evident in translations from Chinese to English. While translations in general can be edited, it is not possible to edit phrases in Chinese. Instead, it is necessary to edit arbitrary sets of characters, which leads to incorrect edits.

Texts written in Greek, Devanagari, Cyrillic and Arabic writings can be automatically transliterated from phonetic equivalents written in the Latin alphabet. The Google Translator browser version offers the option to read phonetically for the Japanese to English conversion. The same option is not available in the paid API version.

For many of the most popular languages, the system has a "text to speech" audio conversion feature that allows you to read a text from a dozen words in that language. In the case of multi-center languages, the message accent depends on the region: from English, in the Americas, most of the Asia-Pacific and West Asia region audio uses a general American accent with a feminine tone, while an accent is used in Europe, Hong Kong, Malaysia, Singapore, Guyana and all other parts of the world British English with a feminine tone, a special accent is used in Australia, New Zealand and Norfolk Island, for the Spanish, in the Americas a Spanish accent from Latin America is used, while in the other parts of the world a Spanish Spanish accent is used. In Portuguese in general, an accent from São Paulo is used, with the exception of Portugal, where its native accent is used. For some low-spread languages, the eSpeak open source voice synthesizer is used. However, production using a voice robot can be difficult to understand.

Criticism

Shortly after launching the translation service, Google won an international competition for English-Arabic and English-Chinese automatic translation.

Translation errors and oddities

Because the Google Translator uses statistical matching to translate, sometimes the translated text may include obvious errors and seemingly meaningless phrases, using common terms for similar but not equivalent common terms in the target language, as with the target language. Latin translation, reversing or altering its meaning of the requested sentence.

Google Translate Community

The Google Translator Community is a platform that aims to help improve the Google Translator service. Volunteers can select up to five languages to help with the best translation. Users can check translated phrases and translate phrases in their language to and from English, helping to improve the accuracy of the translation of rare and complex phrases.