Profile cover photo
Profile photo
Matt Gardner
Matt's posts

A survey of datasets and methods for reading comprehension:

Post has attachment

Post has attachment

Thesis successfully defended.  It feels kind of weird.  Am I really done?

The recommended articles is a nice idea, but as it is it's basically worthless to me.  The reason for this is that it sees that I save a lot of things from Ars Technica and Android Police, and so it helpfully shows me more stuff from those sites in the recommended tab.  The problem is those are exactly the articles that I have already looked at and decided not to save.  I have those sites in an RSS feed, so I already see all of their articles.  Recommending them to me again is worse than useless.  What I would really like to see in the recommended section are articles that I am likely to be interested in and that I am not likely to have already seen.

I'm at a thesis proposal at CMU, and I'm not totally sure what to think of this racial disparity:

Number of white male students in the room: 2 out of about 45 (the rest are almost all Asian (including Indian), maybe 25% female)
Number of white male thesis committee members: 4 out of 4

Does this mean that minority students don't have hope of getting tenure, or that white male students don't have much hope of getting into CMU, or that the racial distribution of tenured faculty is in for a big change?

Post has attachment
What should you do when your scientists come to conclusions that you find politically unsavory? Listen to their evidence? Oh, heavens no, you shouldn't do that. Just insult them and defund them. Obviously.

PhD thesis successfully proposed.  Now to actually finish the work...

If you're interested in seeing the proposal document:

Post has attachment
A really nice paper on tensor factorization models for KB inference. This paper had a big impact on my current research direction.
Wait while more posts are being loaded