The telling difficulty is the trivial and artificial nature of the example of where semantic search out performs traditional search:
For example, shrub vs. tree. If I do a search for decorative shrubs for my yard, and the ideal web page has small decorative trees for my garden, it really should have matched that page and brought it up as a good result. But today Google won’t do it, Yahoo won’t do it, and Live won’t do it. So even in these normal queries there is a lot of value in the linguistics.
The comments after the interview raise some interesting questions about the impact all this will have on Google, and about the technical difficulties of integrating Powerset with live search. Library stalwarts recall&precision even get a mention.
For all the frisson of big money hunting out semantic search, questions remain - does natural language actually capture intentions and meaning? Can the Web provide a reliable fabric for semantic search? The wikipedia page on shrubs is part of that reliable (ish) fabric, but it is constructed by people, who will likely remain the killer app of the Interweb long after Powerset has disappeared into Microsoft.
Related Post:
Widget by [ Iptek-4u ]