Tuesday, December 13, 2011

Do we even need machine translation?

Massive-scale online collaboration is a TED talk given by  Luis von Ahn, known as one of the first people who worked with CAPTCHAs and as the inventor of reCAPTCHA. He argues that machine translation isn't good enough and proposes a crowd-sourcing solution for breaking down language barriers. Interesting stuff!




Here's the website of Duolingo, the translation crowd-sourcing project that was described in the talk. Note that this isn't necessarily antagonistic to our AI approach; the output of this project can be used to provide us with the sentence pairs we so desperately need to train our translation algorithms.

Sunday, December 11, 2011

Quote

No amount of experimentation can ever prove me right; a single experiment can prove me wrong - Albert Einstein

Tuesday, December 6, 2011

The face of a liar

If you liked today's lecture on facial expressions, you'll also probably like this Radiolab episode on deception. Part of the episode is focused on micro facial expressions, which can be used to detect someone wearing a fake facial expression. Paul Ekman, the guy the lecturer mentioned, is featured. (skip the first three minutes if you don't want to hear about a type of snake that plays dead when in danger)

Monday, December 5, 2011

CYK-parser performance

Hi all,

so I ran CYK with Viterbi without smoothing out unknown words and as a result I got:

-- len<=15 --
Number of sentence = 603
Number of Error sentence = 0
Number of Skip sentence = 0
Number of Valid sentence = 603
Bracketing Recall = 31.71
Bracketing Precision = 41.81
Bracketing FMeasure = 36.06
Complete match = 0.66
Average crossing = 1.42
No crossing = 51.41
2 or less crossing = 75.79
Tagging accuracy = 83.71

does this match your findings so far? I want to know before I start smoothing :)

Update:
-- All --
Number of sentence = 603
Number of Error sentence = 0
Number of Skip sentence = 0
Number of Valid sentence = 603
Bracketing Recall = 77.30
Bracketing Precision = 78.17
Bracketing FMeasure = 77.73
Complete match = 21.56
Average crossing = 0.73
No crossing = 70.48
2 or less crossing = 89.39
Tagging accuracy = 92.66

Friendly Reminder

I just want to give a reminder that the registration for the second semester is open and that you should register the courses that you want to do :)

and while we are on topic: any tips on good free choice courses?

Saturday, November 26, 2011

Boardgames / RPGs anyone?

Now for something completely different: KR is over and free time might become a bit less impossible to obtain, so I've got to ask:

Is anyone else interested in boardgames or role playing games among us? Want to start a game group for one of these?

Additional details: From boardgames I'm mostly interested in eurogames (Catan, Puerto Rico etc), although I'm willing to play pretty much anything. For RPGs, I'm currently mostly into indie narrativist games (eg Dogs in the Vineyard) and horror games; but, again, I'm willing to play pretty much anything.

Thanks for reading (and apologies if this is spam to you),
-Nikolas

Friday, November 25, 2011

ELPL - Empirical findings

Hey peeps,

While sifting through the masses of documents about assignment 1, we found that we have to list some empirical findings about the probabilities of words and productions. I've attached our findings in a document. Could anyone check if it matches your own findings?

https://docs.google.com/open?id=0B5e7DAOiLEZwYjhjODFkZGQtMjI1My00Mjg2LTgzY2UtOGYxZjA3OTdjNGQ0

Cheers