Welcome吉祥彩票官网 to Thomas Insights — every day, we publish the latest news and analysis to keep our readers up to date on what’s happening in industry. Sign up here to get the day’s top stories delivered straight to your inbox.
Most of us have at least one story of an unfortunate autocorrect blunder, but still, few people would choose to live without it. Whether autocorrect has helped you catch a typo in a rushed email or missed the mark by just one letter, you can thank Dean Hachamovitch.
Hachamovitch began working for Microsoft in the early 1990s on the Word team, and at the time, there was a function in Word where one could type out a command, press a couple of keys, and the command would be carried out. Hachamovitch thought he could apply this to typing by creating a glossary of common errors and corrections with the spacebar used to trigger a swap.
Hachamovitch and his team then began creating a lengthy dictionary for the tool to reference, from spelling errors to an accidental caps lock. However, a hiccup existed in the handling of obscenity; the Word team didn’t feel comfortable suggesting curse words but also didn’t want to come off as prudish. Their solution was to make a list of words that wouldn’t be noted or suggested by the software.
Today, rather than relying on a master list, autocorrect uses a statistical analysis of public words to determine which one is the best option with which to replace your error. Keyboard proximity, phonetic similarity, and context are all considered when calculating which word to replace the mistake with. It’s an amazing algorithm that could become a bit frustrating when autocorrect keeps insisting you mean duck.
But autocorrect is only getting better; soon it’ll be able to differentiate between casual language among friends and formal communication with a boss.
Image Credit: Thomas Insights