Google has announced its largest-ever expansion of language support for Google Translate, adding 110 new languages to its repertoire.
This development significantly bolsters the platform’s ability to break down language barriers and facilitate global communication.
Before this expansion, Google Translate supported 133 languages.
The addition of 110 new languages is attributed to advancements in AI technology, particularly Google’s PaLM 2 large language model.
According to a Google blog post on Thursday, PaLM 2 played a pivotal role in enabling Translate to learn languages that are closely related to others, such as Awadhi and Marwadi related to Hindi, and French creoles like Seychellois Creole and Mauritian Creole.
The post says, “From Cantonese to Qʼeqchiʼ, these new languages represent more than 614 million speakers, opening up translations for around 8% of the world’s population.
“Some are major world languages with over 100 million speakers. Others are spoken by small communities of Indigenous people, and a few have almost no native speakers but active revitalisation efforts.
“About a quarter of the new languages come from Africa, representing our largest expansion of African languages to date, including Fon, Kikongo, Luo, Ga, Swati, Venda and Wolof.”
Most of the newly added languages are spoken by at least one million people, with several boasting hundreds of millions of speakers.
The post also gives insight into how Google selects languages for the translation service.
It says, ” There’s a lot to consider when adding new languages to Translate — everything from what varieties we offer, to what specific spellings we use.
“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.
“For example, Romani is a language that has many dialects all throughout Europe. Our models produce text that is closest to Southern Vlax Romani, a commonly used variety online. But it also mixes in elements from others, like Northern Vlax and Balkan Romani.
“PaLM 2 was a key piece to the puzzle, helping Translate more efficiently learn languages that are closely related to each other, including languages close to Hindi, like Awadhi and Marwadi, and French creoles like Seychellois Creole and Mauritian Creole.
“As technology advances, and as we continue to partner with expert linguists and native speakers, we’ll support even more language varieties and spelling conventions over time.”
In 2022, Google introduced 24 languages using Zero-Shot Machine Translation, a method where AI models learn to translate between languages without prior examples.
Additionally, the company announced the 1,000 Languages Initiative, aiming to support the world’s most spoken languages with AI models.
The post adds that the addition of these 110 languages marks a milestone for Google Translate, enabling more users worldwide to access accurate and effective translation services across a diverse range of languages.
