Watson & Natural Language Processing

17 February 2011

A John Henry story for the information age, except the humans lose. Ben Zimmer has a summary of the competition between IBM’s Watson computer and two Jeopardy! champions, Ken Jennings and Brad Rutter.

Programming a computer to interpret and respond appropriately to normal human language is really a significant development. Granted that the format of Jeopardy! questions is highly formulaic (among other things, they are pre-classified into categories and each question contains at least two clues) and it’s far from being able to engage in conversation, but it’s still quite impressive.

I’m not going to recount the duel—Zimmer does that quite well—but I will point out one of Watson’s flubs that has personal relevance to me as an American living in Toronto. In the category of “US Cities,” the question, or rather answer, was “Its largest airport is named for a WWII hero. Its second largest for a WWII battle.” Watson buzzed in with, “What is Toronto.” (The correct answer is, of course, Chicago.) When asked how the computer might make such an elementary error, to wit, thinking Toronto was a US city, one of Watson’s programmers explained that since Toronto’s baseball team, the Blue Jays, plays in the American League, the computer might have inferred the city was in the US. Evidently thinking like a human is more subtle than it may seem.

Old English Characters in Windows

Thursday, 27 January 2011

Old English uses a number of letters and punctuation marks, like the thorn þ and the eth ð, that do not exist in modern English. Typing these can be a challenge. This MS Word document has information on how to get your Windows computer to produce these characters, OELetters.doc (721 Kb). (I don’t know the Mac, but if someone sends me info on how to do this on the Mac, I’ll add it to the document.)

If you’re typing for the web, like on this site’s discussion forum, it’s probably best to limit yourself to the most commonly supported characters. The more esoteric characters will probably not be seen on other people’s systems.

If you’re a hardcore user of Old English, you’ll probably want to download the Junicode font and even this keyboard map.

[Updated the linked MS Word document, Jan 2011 — dw]