blog
-
10,000 most frequent words in Greek and Latin canon
While working on the latest release for the CLTK, which now includes stopword builders, I discovered Python’s built-in Counter().most_common() method, which makes creating word frequency lists easy (Greek notebook here,...
-
Tf-idf pairwise similarity in the Greek canon
I may write more about this later, but I have been sitting on this Greek tf-idf pairwise similarity comparison, run on all authors of the TLG against one another, for...
-
Tf-idf pairwise similarity in the Latin canon
Several weeks ago a journalist asked me some interesting questions about tf-idf, which got me thinking about related tasks for, what else, the Latin and Greek authors of the PHI5...
-
Lexical diversity in the Latin canon
Since I had the code laying around from my previous post on Greek lexical diversity, I turned it to the PHI5. Here’s my notebook on Lexical diversity in the Latin...
-
Lexical diversity in the Greek canon
This post is just a quick summary of a little calculation I did with the help of the CLTK’s improved text processing for the TLG. All of my code for...
-
CLTK POS tagging cross–validation
Important! This post contains incorrect accuracy scores. See http://cltk.org/blog/2015/08/02/corrected-stats-pos-tagger-accuracy.html for better information. A few months ago, I began a series of blog posts which reported on the CLTK’s in–progress POS...
-
A human–editable POS–tagged text
Since I have begun talking about POS tagging with the CLTK, my educator contacts have been asking about ways they and their students can contribute. I am happy to share...
-
Affix POS tagging with the CLTK
Important! This post contains incorrect accuracy scores. See http://cltk.org/blog/2015/08/02/corrected-stats-pos-tagger-accuracy.html for better information. Affix tagging looks at the beginning or ending of a word and chooses a POS tag. I’ve worked...
-
TnT POS tagging with the CLTK
Important! This post contains incorrect accuracy scores. See http://cltk.org/blog/2015/08/02/corrected-stats-pos-tagger-accuracy.html for better information. My previous post built on the CLTK’s n–gram taggers and used them in conjunction with each other. Now...
-
N–gram backoff POS tagging with the CLTK
Important! This post contains incorrect accuracy scores. See http://cltk.org/blog/2015/08/02/corrected-stats-pos-tagger-accuracy.html for better information. Since my last post on n–gram part–of–speech taggers for Ancient Greek and Classical Latin, I have been working...