What did you say?

I've been meaning to plug the website Lost In Translation for a long time. Computational Linguistics, better known as Natural Language Processing, concerns itself with the algorithmic, linguistic processing of human language. It is a very tricky field with many problems to solve. While there are good techniques, they are hardly practical. Some of the more basic algorithms are available for use in translation on the web through mechanisms such as babelfish, but only for the most basic of expressions, as Lost In Translation demonstrates. As soon as you introduce complexity in the syntax and meaning of words, these algorithmic methods break down.

What happens when an English phrase is translated (by computer) back and forth between 5 different languages? The authors of the Systran translation software probably never intended this application of their program. As of July 2003, translation software is almost good enough to turn grammatically correct, slang-free text from one language into grammatically incorrect, barely readable approximations in another. But the software is not equipped for 10 consecutive translations of the same piece of text. The resulting half-English, half-foreign, and totally non sequitur response bears almost no resemblance to the original.

Classic Examples:
I'm a little tea pot, short and stout.
translates to
They are a small POTENTIOMETER, short circuits and a beer of malzes of the tea.

a cookie is just a cookie, but fig newtons are fruit and cake.
translates to
biskuit has expert of biskuit, but Newton von Fig is fruit and hardens.

When the moon hits your eye like a big pizza pie, that's amore.
translates to
If the moon fixes its eye like a great vector of Fleischpie of the vector of Pizzapie, is the lover.

These algorithms don't even come close to modeling the linguistic capacity of the human brain, but the research is promising! Of course, even we, humans, sometimes get it wrong, as former US Presidential Candidate George Romney expressed back in 1967 when he said:

I know you believe you understood what you think I said,
but I am not sure you realize that what you heard is not what I meant!