Tuesday, July 16, 2024
HomeNews ReportsGoogle Translate adds 110 new languages including Awadhi, Chhattisgarhi, Marwadi and Pakistani Punjabi using...

Google Translate adds 110 new languages including Awadhi, Chhattisgarhi, Marwadi and Pakistani Punjabi using PaLM 2 AI language model

Till now, Google Translate supported 133 languages, so this expansion is the biggest ever, as per the company, and marks a significant jump in the number of supported languages.

Google is adding support for 110 new languages to Google Translate, the company announced on Thursday. Till now, Google Translate supported 133 languages, so this expansion is the biggest ever, as per the company, and marks a significant jump in the number of supported languages. The company used the help of AI to add new languages for translation services.

The new languages added include Awadhi, Chhattisgarhi and Marwadi from India, and Punjabi (Shahmukhi) from Pakistan.

As per a blog post by Google’s Isaac Caswell, the company used its PaLM 2 AI language model for Google Translate to learn new languages. The company said that the AI model is good at learning new languages which are closely related to other languages. For example, the model learned Awadhi and Marwadi better because of their closeness to Hindi, which is already supported by Google Translate.

Some other major languages added include Afar, Cantonese, Manx, NKo, Tamazight (Amazigh) and Tok Pisin. The blog post said that Cantonese was one of the most requested languages to be added. It said that because Cantonese often overlaps with Mandarin in writing, it’s tricky to find data and train models.

Afar is a tonal language spoken in Djibouti, Eritrea and Ethiopia, and it had the most volunteer community contributions among the languages being added. Manx is the Celtic language of the Isle of Man which almost went extinct with the death of its last native speaker in 1974. But the language is being revived in the island. NKo is a standardized form of the West African Manding languages that unifies many dialects into a common language.

Punjabi (Shahmukhi) is the variety of Punjabi written in Perso-Arabic script (Shahmukhi), and is the most spoken language in Pakistan. Tamazight (Amazigh) language is spoken across North Africa. Tok Pisin is an English-based creole and the lingua franca of Papua New Guinea.

Isaac Caswell said that about a quarter of the new languages come from Africa, representing the company’s largest expansion of African languages to date, including Fon, Kikongo, Luo, Ga, Swati, Venda and Wolof. He wrote, “From Cantonese to Qʼeqchiʼ, these new languages represent more than 614 million speakers, opening up translations for around 8% of the world’s population.”

He told the Verge in an interview that the new languages are spoken by at least one million people, while several are spoken by hundreds of millions of people. He also wrote that some languages are spoken by small communities of Indigenous people, and a few have almost no native speakers but active revitalization efforts. 

The blog post added that there are a lot of things to consider while adding new languages to Google Translate, like what varieties to offer, what specific spellings we use etc. He said, “Languages have an immense amount of variation: regional varieties, dialects, different spelling standards. In fact, many languages have no one standard form, so it’s impossible to pick a “right” variety. Our approach has been to prioritize the most commonly used varieties of each language.”

Currently, Google Translate supports 20 Indian languages. These include Assamese, Bengali, Bhojpuri, Dogri, Gujarati, Hindi, Kannada, Konkani, Maithili, Malayalam, Marathi, Meiteilon (Manipuri), Mizo, Nepali, Odia, Punjabi, Sanskrit, Tamil, Telugu and Urdu. Seven languages including Sanskrit were added in 2022.

Join OpIndia's official WhatsApp channel

  Support Us  

Whether NDTV or 'The Wire', they never have to worry about funds. In name of saving democracy, they get money from various sources. We need your support to fight them. Please contribute whatever you can afford

OpIndia Staff
OpIndia Staffhttps://www.opindia.com
Staff reporter at OpIndia

Related Articles

Trending now

Recently Popular

- Advertisement -