tehgeekmeister’s blog

March 12, 2008

“a new kind of graded reader”

Filed under: Uncategorized — tehgeekmeister @ 3:41 am

original post is here, by james tauber.  using simulated annealing on a tagged greek new testament corpus, he generates a progression which maximizes clauses comprehensible as opposed to vocabulary learnt.  i’ve been wanting to do something similar for years, but have only recently begun to develop the requisite discipline, programming skills, and math to consider approaching a problem like this.  i’d like to use a similar idea (not sure if i’d stick with SA — I don’t know enough about statistics or machine learning to know if it’s best yet) in a more integrated approach.  this, however, is a very long term goal — so don’t expect to see much of anything soon.  =P

Advertisements

1 Comment »

  1. Actually, I’m not using SA at the moment, but rather trying a variety of deterministic algorithms that give much faster (albeit not always as good) results.

    I’m happy to share code and discuss these ideas further.

    Comment by James Tauber — March 13, 2008 @ 5:35 pm


RSS feed for comments on this post. TrackBack URI

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

Create a free website or blog at WordPress.com.

%d bloggers like this: