Posts Tagged ‘lti’

MS in Language Technologies

Posted: 30 June 2008 in Uncategorized
Tags: , , , , , ,
5

I just completed the final requirements of my Masters degree today (the details of which I will save for a future post).  It has been a difficult road, and I’m glad it’s done.  I didn’t attend any sort of graduation ceremonies, because I don’t go for that sort of thing — at all.  Until today, it didn’t feel like the weight was off my shoulders.  Now I actually feel like celebrating!  But I won’t, because I’m a nerd.  I’m currently celebrating by working on a programming puzzle.  And surfing the blagoblag.

I still have a couple months of servitude to complete the requirements of my fellowship, but the degree is mine.

Who created OpenEphyra?

Posted: 16 February 2008 in Uncategorized
Tags: , , , , , , , , ,
6

OpenEphyra is a question answering (QA) system developed here at the Language Technologies Institute by Nico Schlaefer. He began his work at the University of Karlsruhe in Germany, but has since continued it at CMU and is currently a PhD student here. Since it is a home-grown language technologies package, I decided to check it out and play around. This is the first QA system I have used that wasn’t integrated in a search engine, so this isn’t exactly an expert review.

Getting started in Windows (or Linux or whatever) is pretty easy if you already have Apache ant and Java installed. Ant isn’t necessary, but I recommend getting it if you don’t have it already. It’s just handy. First, download the OpenEphyra package from sourceforge. The download is about 59 MB and once it’s done unpack it in whatever directory you want. Assuming you have ant installed, all you have to do is type ant to build it, though you may want to issue ant clean first. I had to make one slight change to the build.xml file to get it to run, which was on line 55: <jvmarg line="-server& #13;-Xms512m& #13;-Xmx1024m"/>, which had to be changed to <jvmarg line="-server -Xms512m -Xmx1024m"/>. Easy enough. Then to run it, all you have to do is type ant OpenEphyra.

After taking a short bit to load up, you can enter questions on the command line. Based on what I can tell from the output, it begins by normalizing the question (removing morphology, getting rid of punctuation). Then it determines the type of answer it is looking for, like a person’s name or a place and assigns certain properties to what it expects to find. Next it automatically creates a list of queries that are sent to the search engine(s). The documentation indicates that the AQUAINT, AQUAINT-2 and BLOG06 corpora are included (at least preprocessing is supported), but there are searchers for Google, Wikipedia, Yahoo and several others. Indri is a search engine which supports structured queries and OpenEphyra auto-generates some structured queries from what I saw playing around. After generating the queries, they are sent to the various searchers and results are obtained and scored. Finally, if you’re lucky, you get an answer to your question.

Here are the results of screwing around with it for a few minutes:

  • Who created OpenEphyra?
    • no answer (sorry, Nico)
  • Who invented the cotton gin?
    • Eli Whitney
  • Who created man?
    • God
  • What is the capital of Mongolia?
    • Ulaanbaatar
  • Who invented the flux capacitor?
    • Doc Brown (awesome!)
  • Who is the author of the Mendicant Bug?
    • Zuckerberg — damn you, Facebook! :(
  • How much wood can a woodchuck chuck?
    • no answer (correct)
  • What is the atomic number of Curium?
    • 96 (also correct)
  • Who killed Lord Voldemort?
    • Harry (correct, but partial)
  • How many rings for elven kings?
    • 3021 (so, so very wrong)

Fun stuff! It’s not anywhere near perfect, but there are definite uses and the thing is ridiculously easy to install and use. Also, it’s in Java, so you can integrate it with your own system with very little effort. Depending on what sort of question you are looking for answers to, you get various levels of results. Factual questions about geography and people tend to do better than questions about numbers and fiction, as you might expect. Also, why-questions are not supported.

Another bonus is the project is open source, so if you’re into QA, you can help develop it.

Smiley TG

Posted: 21 September 2007 in Uncategorized
Tags: , , , , , ,
1

I mentioned TGs in a previous post.  To refresh your  memory, they are the school of computer science’s big departmental parties (actually thrown by the student organization, Dec/5).  The name has been generalized to any party thrown in the department.  Today’s was the Smiley TG, celebrating the birthday of the smiley, invented by Scott Fahlman, a professor in my department.  Planned as well as all things are, today is also the annual picnic for my department!  So I went to the TG, where I was almost completely without friends.  So I drank a Dogfish Head 60 Minute IPA and left.  But not before grabbing some swag and snapping a pic of the pandemonium.

Smiley Swag

 

Smiley TG in the school of computer science at Carnegie Mellon University

:-) x 25

Posted: 18 September 2007 in Uncategorized
Tags: , , , , , , , ,
1

A professor in my department (primarily affiliated with the LTI and the CSD, but also the MLD and HCII) invented the smiley 25 years ago on a bboard here at CMU. The fateful message that spawned the smiley is reproduced below [source]:

19-Sep-82 11:44    Scott E  Fahlman             :-)
From: Scott E  Fahlman <Fahlman at Cmu-20c>
 
I propose that the following character sequence for joke markers:
        
:-)
        
Read it sideways.  Actually, it is probably more economical to mark
things that are NOT jokes, given current trends.  For this, use
        
:-(

In honor of the 25th birthday of the smiley, the CS department is holding a TG where Scott will inaugurate an annual Smiley Prize. I’m probably not going to be able to make that, though, on account of other engagements.

(more…)

Leinenkugels Sunset Wheat

Posted: 21 August 2007 in Uncategorized
Tags: , , , , ,
1

Tonight was the reception “TG” for new students of the Language Technologies Institute.  TG is the general term given to parties thrown in the department of computer science at CMU.  Typically TGs are thrown on Fridays by the student organization Dec/5.  So TG as in TGIF.

So anyhow, I tried a new beer that I hadn’t heard of before called Leinenkugels Sunset Wheat.  I was given a tip prior to coming to the TG that Leinenkugels was the mystery beer.  After a quick search on ratebeer.com, I found that Leinenkugel has one good beer and a whole lot of crap.  Smart money was on the crap being the pick.  Unfortunately, this was correct.  I even guessed the correct specimen of crap:  the Sunset Wheat.

So I decided to taste it so I could add another beer to my rating list.  My reaction was immediate.  Here is the comment I posted on the ratebeer page for this beer:

“I was immediately struck by a similarity to Flintstones vitamins. It was so intense I exclaimed. This beer was really atrocious. On the up side, it didn’t linger very long on the palate. This is a drain pour.”

I stand by this assessment.  After I posted my comment I perused the other comments to see if people agreed with me.  What I found was great.  A few of the tastier specimens I came across are below:

“There are aromas & flavors in this that just don’t belong in a beer. Tastes like the milk left over after eating a bowl of Fruit Loops was poured into my beer. And worse, the fruit taste is very artificial. Maybe it wouldn’t be bad on a hot day, but I think i’m going to avoid this one for now.

“If I got really drunk on beer Friday, woke up on Saturday and ate some Fruity Pebbles then threw up…this is what it would taste like.”

“On tap. Smell is 100% Fruity Pebbles Cereal. It is uncanny – as though it is liquid Fruity Pebbles. Cloudy golden appearance with no lastin head. Reminds me more of a Hefe than an American Wheat. Really distinctive orange flavor. Almost tastes like a candy beer. Very sweet taste.”

“not so good. Had a flavor of jelly beans totally nasty. Might be the worst beer Ive tasted”

Scanning just a few more pages of comments I found 8 more references to Fruity Pebbles.  I think the key here is that distinct artificial fruit flavor they put in jelly beans, flintstones vitamins and that cereal.  So yeah, it sucked.