BGU NLP - Morphological Disambiguation Package for the Medical Domain

Medical Lexicon by Raphael Cohen

August 2012

This is an extension of the Morphological Disambiguator (Tagger) by Adler et al.:

Meni Adler and Michael Elhadad, An Unsupervised Morpheme-Based HMM for Hebrew Morphological Disambiguation, ACL 2006 pdf.
Meni Adler, Yoav Goldberg, David Gabay and Michael Elhadad, Unsupervised Lexicon-Based Resolution of Unknown Words for Full Morphological Analysis, ACL 2008 pdf
Yoav Goldberg, Meni Adler and Michael Elhadad, EM Can Find Pretty Good HMM POS-Taggers (When Given a Good Start), ACL 2008 pdf

The tagger itself relies on the lexicon and morphological analyzer from the Mila Knowledge Center.

License
Download
Usage

License

Morphological Disambiguation Package for the Medical Domain is distributed under a GPL license.

    EasyFirst is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation, either version 3 of the License, or
    (at your option) any later version.

    This program is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU General Public License for more details.

    See the GNU General Public License.

Download

Tagger + precompiled medical lexicon (contact us).
The prerequisites are java 1.6.

Use

Tag a file or a directory with morphological tags in bitmask form:

Usage:    tagMedical.sh [input file/dir] [output file/dir]
Example:  tagMedical.sh  input input.tagged

Resolve Bitmask (optional)


Usage:   python resolve_bitmask.py [input file]
Example: python resolve_bitmask.py input.tagged

- This will resolve the bitmask into human readable form (works only for a single file).

Last modified August 7, 2012