I came across this article in the New York Times today, regarding the NELL system being developed at CMU – valiant efforts along an important path.
The concluding comments are interesting:
“When Dr. Mitchell scanned the “baked goods” category recently, he noticed a clear pattern. NELL was at first quite accurate, easily identifying all kinds of pies, breads, cakes and cookies as baked goods. But things went awry after NELL’s noun-phrase classifier decided “Internet cookies” was a baked good. (Its database related to baked goods or the Internet apparently lacked the knowledge to correct the mistake.)
NELL had read the sentence “I deleted my Internet cookies.” So when it read “I deleted my files,” it decided “files” was probably a baked good, too. “It started this whole avalanche of mistakes,” Dr. Mitchell said. He corrected the Internet cookies error and restarted NELL’s bakery education.”
Seems like a good fasioned case of lacking grounding in active experience… data on the www isn’t really a substitute for hard earned experience, no matter how much one may hope for that!