FreshNotes: Web 2.0 company using computational linguistics

FreshNotes (currently in alpha) uses basic named entity extraction and maybe information extraction to produce a website that allows to search and navigate relationships between people and/or topics. The interface, but of course it is all pre-baked at the moment.

From the CL point of view, I can see that there is very little smarts in the system yet. Only people’s full names are detected, I don’t see any implications of coreference resolution and the relationship is determined by the names proximity and possibly frequency of co-occurrence. Topics are basic search phrases. People have photographs, which are either licensed from the 3rd party (most probable option) or manually produced.

It is quite possible that even this would be sufficient to make the website interesting from users’ point of view. Or maybe, they just did not get to it yet. But the promise on the website is much grander and so far I do not see it being fulfilled with what they are showing. I think they would have trouble scaling past the many manual steps currently required to connect the knowledge.

FreshNotes presented last Tuesday at the New York Tech Meetup group, and some people have since blogged about their opinion (e.g., Mark Crofton).

Update (7th of November, 2006) - Company is now Knover and is in beta.