videos on the tournament ’ s official website . The latest developments come off the back of work by IBM to produce AI-generated highlights packages by using crowd noise and contextual data to determine the most exciting points of a match . IBM first pioneered the use of AI to curate video highlight reels in 2017 , using gesture recognition and crowd noise to help build highlights videos .
To develop the new feature , experts from IBM iX , the experience design arm of IBM Consulting , worked with The All England Club to leverage foundation models from watsonx , IBM ’ s enterprise AI and data platform , to train the AI in the unique language of tennis .
Work began with watsonx . data , a data store that connects disparate data sources and allows developers to filter the data for things like profanity , hate speech or personally identifiable information . For AI Commentary , the team drew source material from nearly 130 million documents .
The data was then used to train a large language model chosen from watsonx . ai , a next-generation studio for building and training generative AI models for business use cases . The IBM team then fine-tuned the model , adding the specific domain expertise of Wimbledon , including the use of unique Wimbledon nomenclature , such as “ gentlemen ’ s draw ” rather than “ men ’ s draw .”
“ We are teaching the large language model the language of tennis , we are making sure it knows what a forehand is , a backhand is , and then also training it in the language of Wimbledon ,” Farrar explains . “ It ’ s just the
technologymagazine . com 135