Brown corpus
Intensive Python class for Linguists (for corpuslinguistics, language data processing and manipulation etc.)
11/16/11 17:55 Filed in: Info
I am offering an intensive class for the LING519 students, all the Linguist List people, and whoever might be interested, this Saturday 19th of Nov. 2011 at 10 AM Eastern Time in Cooper, the LinguistList Suite. We plan to meet for 4 hours or more, depending on speed and interest. Let me know, if you are interested. If you want to join us, let me know. I will share the screen and the audio already with Zadar, we can include you, if you cannot come. The topics covered might be:
Intro to Python 3
Using Komodo Edit 6.x
Processing corpora like the Brown corpus (raw text with slash-pos, or TEI XML), the Penn Treebank, the Croatian Language Corpus etc.
Generating statistical models and profiles: frequency profiles, N-gram models
Calculating significance, mutual information, relative entropy, …
Simple Finite State Machines
Simple Parsers
Generating outputs of analyses: CSV, HTML, XML, etc.
…
DC
Read More...
Intro to Python 3
Using Komodo Edit 6.x
Processing corpora like the Brown corpus (raw text with slash-pos, or TEI XML), the Penn Treebank, the Croatian Language Corpus etc.
Generating statistical models and profiles: frequency profiles, N-gram models
Calculating significance, mutual information, relative entropy, …
Simple Finite State Machines
Simple Parsers
Generating outputs of analyses: CSV, HTML, XML, etc.
…
DC
Read More...