Tuesday, August 5, 2008


Hi, I'm Rob.

I've been working on stuff related to Open Mind since 2005, but I've had a bit of a low profile recently, because I thought I was going to go work on a different research project after I finished my master's thesis last year. After several months of dabbling in other projects and getting nowhere interesting, I found myself pulled back into OMCS. Moral of the story: if your grad school career ain't broke, don't fix it.

Probably the most visible things I've done are: I put OMCS back on the Web, replacing the 2000-era web site with a Rails site called Open Mind Commons. (When I left, I passed the torch to Ken, and he re-did it in Django, making the code incredibly cleaner in the process.) Also, along with Catherine Havasi, I developed AnalogySpace, the reasoning tool that learns from patterns in ConceptNet and comes up with the "Open Mind wants to know..." questions.

So now I'm back, and my focus is on the multilingual aspect of OMCS. We've got the infrastructure we need to build a ConceptNet in any language. Now our reasoning tools need to catch up.

I've seen the messages on the mailing list speculating that OMCS is stagnating. Well, it's not. It's changing in huge ways on our end, but it takes a while before we can put new features on the Web site. After all, we'd prefer the Web site to stay up.

But I understand that our users want to be in the loop. So I'm planning to write a few blog posts over the next few days about the new multilingual features I'm working on. Stay tuned.


Anonymous said...

I'd like to see Open Mind get more attention. First I think it needs some work to improve the usability and speed. Then how about making a Facebook Application, so that people can add a widget to their profile page which could allow visitors to submit different types of knowledge? Perhaps allow them to show their "score" on their profile, in terms of the number of contributions. People seem to like this competitive aspect--like trying to have more "friends" than their peers…

have you bulk loaded "knowledge" by performing pattern searches across web pages? I could easily write such an app to do that. The results would need to be edited a bit--which would be a perfect job for members to do. I think you need more robust editing features. I made a mistake and wrote "ance" instead of "acne" when submitting something, but I don't see anyway to fix my error. What does "Fix" do? Just flag it for an admin? Maybe allow the community greater control; that is, allow us to fix things and allow others to police our edits with voting…

Is there a stats page? how about some stats like this?

I'd like to contribute more to this project, and I'm sure many others would too. Have you thought of delegating more to the community, instead of restricting control to a couple of people so seems to be busy with other projects?

Anonymous said...

I agree 100% with all of the above :)

Rob Speer said...

We're working on changes that would let us implement some of your recommendations, such as giving the community the ability to decide how to correctly phrase an assertion.

We've been delegating translation work to people who know the language, and we may be able to decentralize that even more soon.

A stats page that's not as useful as it could be is at: http://commons.media.mit.edu/en/stats/

A Facebook app sounds like a good idea, but Facebook is a complex platform with even more complex social dynamics. I believe that maintaining a Facebook app would be a full-time job in itself. It is possible that we could make it happen, though, if we happen to find an undergrad who's skilled enough to implement it and reliable enough to follow through.