English is not typically considered a tonal language, but the following seven-word sentence can give you an idea for how difficult it can be to program a computer to understand the nuances that humans take for granted. As you read the following sentence, consider how the meaning shifts depending on which of the seven words you emphasize -- seven words, seven different interpretations for the sentence.

"I never said she stole my money."

I encountered this sentence several times while studying linguistics and artificial intelligence because it is a simple demonstration of why language is so difficult for computers to understand or generate. Wikipedia offers these seven interpretations.

  • "I never said she stole my money" - Someone else said it, but I didn't.
  • "I never said she stole my money" - I simply didn't ever say it.
  • "I never said she stole my money" - I might have implied it in some way, but I never explicitly said it.
  • "I never said she stole my money" - I said someone took it; I didn't say it was she.
  • "I never said she stole my money" - I just said she probably borrowed it.
  • "I never said she stole my money" - I said she stole someone else's money.
  • "I never said she stole my money" - I said she stole something of mine, but not my money.

Perhaps you can think of even more? Consider the ways that authors attempt to evoke these interpretations without resorting to italics or bolding. It's not trivial! Consider how quickly children learn to differentiate and utilize these forms. In this case, intonation is being used to indicate the target of the sentence's overall negation, but that's just one way that English uses tone. No wonder it's hard to make machines that can understand natural language!

0 TrackBacks

Listed below are links to blogs that reference this entry: Natural Language Processing: Intonation.

TrackBack URL for this entry: https://www.mwilliams.info/mt5/tb-confess.cgi/7541



Email blogmasterofnoneATgmailDOTcom for text link and key word rates.

Site Info