Error Cascades in Semantic Classification

Here’s an interesting piece from the New York Times on the effort to develop intelligent machine categorisation. Most interesting is the way that early mistakes in the computer’s interpretation of content leads to mistake “avalanches” because prior learning is used to make inferences about future learning.

“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.”

0 Comment so far

Commenting is not available in this weblog entry.

Comment Guidelines: Basic XHTML is allowed (<strong>, <em>, <a>) Line breaks and paragraphs are automatically generated. URLs are automatically converted into links.