Better Use of Lemmatization/Stemming

Several Changes detailed in the revision notes. The biggest changes are:

1. Stemming has been removed from the distributional system. This has been replaced with the lemmatization procedures used to create the .terms files. So for statistical purposes the following forms will be mapped to the same lemma: speech recognizer, recognizer of speech, speech recognizers, sr, srs
2. The .out_term_list files have a new format, tab separated values. The first field is the lemma, the other fields are the various forms of the lemma observed in the input file.

final version of 2,1 before new changes

final version of 2,1 before new changes

Termolator .02 beta

This release has a simpler file structure and is 100% Python3. This version includes legal topic specific improvements. It also provides a way to save the results of the Relevance Filter in order to use this part of the program more efficiently.

v.01

Fixed formatting in tchunk program -- The python strip program was re…