Skip to content

ePoGeeS FAQs

Why class-based n-grams instead of type-based?  Why stochastic beam search instead of genetic algorithms?  Well, partly because those had been done before.  But mostly because I felt like it.  I’m doing this in my spare time, late at night or on weekends or during holidays.  I knew class-based n-grams were harder, but they sounded interesting.  I’d coded genetic algorithms before (once in JavaScript on in a web browser an old PowerPC – HA!) so I wanted to try another local search algorithm.  I’m in it for the FUN.

Why an applet?  I was influenced by Eric Scovel’s efforts at making gnoetry available as well as by Charles Hartman’s publically available programs.  I realize there are good reasons why many researchers don’t make their programs available – not least of which is there’s a serious lack of fun in making it usable and fixing bugs and adding features that end-users demand.  But I’m also feeling that old-school Hacker “giving back” ethic.  So I swore I’d ignore feature requests and complaints about usability.  That’s why I think of it as my sketchbook: it’s not a tool I’m building for other people to use; it’s something I built for myself to use, and which others are welcome to borrow and try out.

why computational poetry

My friend Linda was once dating a guy named Jimmy who wanted to be a comedian.  So Linda went to see Jimmy at the local comedy club’s amateur hour.  Afterwards I asked Linda how it went.  Well, she said, he juggled for a while, then he stopped and told some jokes.  But the jokes weren’t that good.  He should have kept juggling the whole time, Linda said.  The jokes still wouldn’t have been good, but then you could have said: at least he juggled the whole time!

So there you have it.  My poetry isn’t that good, but I’m juggling the whole time.