It is also possible to enter searches in a source language that are first translated to a destination language allowing you to browse and interpret results from the selected destination language in the source language. The service limits the number of paragraphs, or range of technical terms, that will be translated. With these new updates, these people can now more easily access the entire multilingual web in their own language. There are currently about 100 million people who speak Armenian, Azerbaijani, Basque, Georgian and Urdu. This will help Google build better machine translation systems especially for languages that are not well represented on the web. If you are a translator, then you can contribute translation memories with the Translator Toolkit. If you notice an incorrect translation, you can click "Contribute a better translation" to correct it. You can help Google Translate improve translation quality as well. Google also used parallel corpora from the European Union and other institutions which had released large amounts of data. These included initially the 6 languages of the United Nations (English, French, Spanish, Chinese and Russian) because the UN had released large sets of parallel corpora which contained sentences aligned from one language to another. "Good working languages" are those for which Google could find a lot of bilingual, aligned data. The translations maybe less fluent than other languages as Google has gathered less data to feed its statistical machine translation system, but they should still help you understand the multilingual web. These languages are still in alpha status, though. These new languages bringing the total number of languages on Google Translate to 57. ![]() You can find the five of them on Google Translate. Google has just added five new languages to its machine translation platform: Azerbaijani, Armenian, Basque, Urdu and Georgian.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |