Facebook unveils 1st multilingual Machine Translation model

Facebook unveils 1st multilingual Machine Translation model

Fb has open-sourced an AI model that may translate between any pair of 100 languages with out first translating them to English as an middleman step. This new model introduced by Facebook AI directly trains Chinese to French data to better preserve meaning.

Facebook has actually unveiled an AI translator which has learned 100 languages. Stating that breaking language barriers through machine translation (MT) is one of the most important ways to bring people together, and provide information on COVID-19, Facebook said that the single multilingual model performs equally as well as traditional bilingual models and managed to get 10 BLEU point improvement over English-centric multilingual models. In a blog post, Facebook AI researcher Angela Fan explained how she and her team set about creating a massive "many-to-many" dataset containing more than 7.5 billion sentences in 100 different languages.

"For years, AI researchers have worked to build a single universal model capable of understanding all languages in different tasks". This data was gathered using open-source data mining tools such as ccAligned, ccMatrix and LASER, and then split into 14 distinct language groups based on parameters such as linguistic classification, geography and cultural similarities. Using novel mining strategies to create translation data, Facebook built the first truly "many-to-many" data set with 7.5 billion sentences for 100 languages. For instance, one group would include languages spoken in India, like Bengali, Hindi, Marathi, Nepali, Tamil, and Urdu, ' Fan wrote.

WhatsApp is preparing to launch a new feature to compete with

Further, to connect the languages of different groups, a small number of bridge languages are identified, like a group of Hindi, Bengali, and Tamil for Indo-Aryan languages. And then, parallel training data for all possible combinations of these bridge languages are mined. To facilitate people's understanding, the team chose to create translation bridges.

Fan noted that the new model has more accuracy than other systems because it does not rely on English as the intermediate language for translation.

In a statement, Facebook AI said, "Deploying M2M-100 will improve the quality of translations for billions of people, especially those that speak low-resource languages".

Kim Kardashian Opens Up About 2016 Paris Robbery In Emotional Interview
The new season of My Next Guest Needs No Introduction is set to premiere on Netflix on Wednesday, 21 October. The Keeping Up with the Kardashians star broke down tears as she recalled what happened.

Related Articles