Debian Codegraph @

data/fa/README

raw
1
2 Persian Link Grammar
3 --------------------
4 By Jon Dehdari
5 Brigham Young University Linguistics Department
6 2003-2005
7
8
9 This README is for 'persianlg', a Persian (Farsi) implementation of the
10 Link Grammar (LG) syntactic parser. The LG Parser is a new approach to
11 parsing sentences, and was developed at Carnegie Melon University. The
12 parser works by simply linking words together. Directionality and
13 distance are the primary constraints given, and are found in the 4.0.dict
14 file.
15
16 The Persian PersianLG implementation is the first full non-English
17 implementation, to my knowledge. It works a little differently than
18 the English version, due to the more complex word structure.
19 Morphological pre-parsing is required, either by hand, using the
20 included stemmer (stemmer.pl) [1], or using the Persian-pckimmo
21 morphology engine. The LG-Soar framework, developed in the BYU Soar
22 research group, has tied both the LG parser and the PC-Kimmo engine
23 together, to provide seamless integration of morphology and syntax.
24 Thus manual morphology pre-parsing is not necessary, nor is cutting
25 and pasting pckimmo output to the link-parser input.
26
27 For example, an unvoweled text like 'mn midAnm kh tu rfti.' (I know
28 that you went), should go into the LG parser as 'mn mi dAn m kh tu rf t i.'
29 See the orthography.txt file for the romanization scheme used.
30
31 This package is Free Software, licensed under Lesser General Public
32 License v.2.1 (www.fsf.org). See LICENSE for details. Note: the
33 original PersianLG was made available under GPLv2; but, as of 2014,
34 Jon Dehdari has consented to changing the license to LGPLv2.1 so that
35 it can be included with the main Link Grammar project.
36
37
38 [1] The stemmmer is located in the /morphology/fa directory. An
39 example usage is:
40
41 ./persianparse.sh 'man midAnam keh tu rafti.'
42
43 or, equivalently:
44
45 echo -e 'man midAnam keh tu rafti.\n' | ./stemmer.pl -u | link-parser fa
46
47 See also:
48 https://github.com/jonsafari/perstem