OT: Big Ten Releases Written by Computer
In my laundry list of Google Alerts, I had a bit of a doosy show up today. The finale to the Michigan/Iowa game was a side story in Business Week's particle on Are Sportswriters Really Necessary.
Below are the opening lines of three stories written about a recent college baseball game. Two are from schools' sports information departments. The other was produced by software that takes box scores and spits out news articles. Which one was done by machine?
a) "The University of Michigan baseball team used a four-run fifth inning to salvage the final game in its three-game weekend series with Iowa, winning 7-5 on Saturday afternoon (April 24) at the Wilpon Baseball Complex, home of historic Ray Fisher Stadium."
b) "Michigan held off Iowa for a 7-5 win on Saturday. The Hawkeyes (16-21) were unable to overcome a four-run sixth inning deficit. The Hawkeyes clawed back in the eighth inning, putting up one run."
c) "The Iowa baseball team dropped the finale of a three-game series, 7-5, to Michigan Saturday afternoon. Despite the loss, Iowa won the series having picked up two wins in the twinbill at Ray Fisher Stadium Friday."
So yeah. I was able to pick out which one it was (follow the link to find out yourself). But still. It's crazy to think that with just the stats of the game, an entire release was formulated without spelling errors or human intervening. Crazy.
I'll say B, just a guess.
EDIT: Chalk one up for bleek-daddy.
Oh yeah, none of them, because they're all accurate.
Those who do follow through, I do make the "Chris Berset for Johnny Bench" mention in the comment, JUST IN CASE THE SELECTION COMMITTEE READS IT.
It doesn't have the small unnecessary bits that don't involve stats (references to the " historic Ray Fisher Stadium") or reference to related games in the weekend series.
Still doesn't change the fact that it's pretty cool.
Last week? Week before? I was unaware of how they were doing it, just that they were. As MFreak says, it lacks all the color that actually makes sports reporting interesting and different than reading the box scores yourself, but maybe I'm a freak from wanting to read the box scores....
for smaller market newspapers who need side articles on a budget
It's not really that hard to pick out. It would be a mistake for anyone to invest in this because the articles are bound to become monotonous after a while. I'm sure it has a huge database of descriptors, but it always follows the same basic language assembly rules.
April 29th, 2010 at 11:43 PM ^
I guessed B, but the plug in A made me pause a little bit.