Source: New Scientist, Oct 2012
Created by sports fan Greg Lee at the University of Alberta in Canada, Scores can tap into a stash of sporting stories to find relevant anecdotes that a commentator might not have thought of.
The idea came to Lee when he found himself choosing between matches on TV based on the commentary rather than the teams. Good commentators insert stories, he says. “As a viewer I was wanting them to tell me something interesting.” The approach could also provide believable commentary to sports video games.
He and his team initially experimented with baseball commentary. During a match in which one team is trailing by four runs in the ninth inning, for example, the system might suggest an anecdote about the Los Angeles Dodgers, who came back to tie a game from the same situation in 2006 by hitting four consecutive home runs.
The system works by matching the features of a live event – such as the teams, key players, the score and the remaining time – against a database of available stories. Once stories that include some of those features are found it selects the few that are most relevant and suggests them to a human commentator.
The challenge is in evaluating the relevance of candidate stories and ranking them. Lee’s system uses machine-learning techniques to do this. The most important feature was the teams involved and the second was the difference in number of runs.