vumix/commit

dutch stop words from snowball

authorMichiel Hildebrand
Mon Apr 23 15:03:34 2012 +0200
committerMichiel Hildebrand
Mon Apr 23 15:03:34 2012 +0200
commite7e2d4017c35f2dc47a92ab2ce37ae446ccf5d1d
treebb182a35fbea2d8652e30de0bbe3e6e15938ea47
parent697d20b2b0a245e51de38e69923e63c9111fcfb9
Diff style: patch stat
diff --git a/lib/stop_words.pl b/lib/stop_words.pl
new file mode 100644
index 0000000..48834d2
--- /dev/null
+++ b/lib/stop_words.pl
@@ -0,0 +1,116 @@
+:- module(stop_words,
+	  [stop_word/2]).
+
+:- multifile
+	stop_word/2.
+
+/* http://snowball.tartarus.org/algorithms/dutch/stop.txt */
+
+stop_word(dutch, de).
+stop_word(dutch, en).
+stop_word(dutch, van).
+stop_word(dutch, ik).
+stop_word(dutch, te).
+stop_word(dutch, dat).
+stop_word(dutch, die).
+stop_word(dutch, in).
+stop_word(dutch, een).
+stop_word(dutch, hij).
+stop_word(dutch, het).
+stop_word(dutch, niet).
+stop_word(dutch, zijn).
+stop_word(dutch, is).
+stop_word(dutch, was).
+stop_word(dutch, op).
+stop_word(dutch, aan).
+stop_word(dutch, met).
+stop_word(dutch, als).
+stop_word(dutch, voor).
+stop_word(dutch, had).
+stop_word(dutch, er).
+stop_word(dutch, maar).
+stop_word(dutch, om).
+stop_word(dutch, hem).
+stop_word(dutch, dan).
+stop_word(dutch, zou).
+stop_word(dutch, of).
+stop_word(dutch, wat).
+stop_word(dutch, mijn).
+stop_word(dutch, men).
+stop_word(dutch, dit).
+stop_word(dutch, zo).
+stop_word(dutch, door).
+stop_word(dutch, over).
+stop_word(dutch, ze).
+stop_word(dutch, zich).
+stop_word(dutch, bij).
+stop_word(dutch, ook).
+stop_word(dutch, tot).
+stop_word(dutch, je).
+stop_word(dutch, mij).
+stop_word(dutch, uit).
+stop_word(dutch, der).
+stop_word(dutch, daar).
+stop_word(dutch, haar).
+stop_word(dutch, naar).
+stop_word(dutch, heb).
+stop_word(dutch, hoe).
+stop_word(dutch, heeft).
+stop_word(dutch, hebben).
+stop_word(dutch, deze).
+stop_word(dutch, u).
+stop_word(dutch, want).
+stop_word(dutch, nog).
+stop_word(dutch, zal).
+stop_word(dutch, me).
+stop_word(dutch, zij).
+stop_word(dutch, nu).
+stop_word(dutch, ge).
+stop_word(dutch, geen).
+stop_word(dutch, omdat).
+stop_word(dutch, iets).
+stop_word(dutch, worden).
+stop_word(dutch, toch).
+stop_word(dutch, al).
+stop_word(dutch, waren).
+stop_word(dutch, veel).
+stop_word(dutch, meer).
+stop_word(dutch, doen).
+stop_word(dutch, toen).
+stop_word(dutch, moet).
+stop_word(dutch, ben).
+stop_word(dutch, zonder).
+stop_word(dutch, kan).
+stop_word(dutch, hun).
+stop_word(dutch, dus).
+stop_word(dutch, alles).
+stop_word(dutch, onder).
+stop_word(dutch, ja).
+stop_word(dutch, eens).
+stop_word(dutch, hier).
+stop_word(dutch, wie).
+stop_word(dutch, werd).
+stop_word(dutch, altijd).
+stop_word(dutch, doch).
+stop_word(dutch, wordt).
+stop_word(dutch, wezen).
+stop_word(dutch, kunnen).
+stop_word(dutch, ons).
+stop_word(dutch, zelf).
+stop_word(dutch, tegen).
+stop_word(dutch, na).
+stop_word(dutch, reeds).
+stop_word(dutch, wil).
+stop_word(dutch, kon).
+stop_word(dutch, niets).
+stop_word(dutch, uw).
+stop_word(dutch, iemand).
+stop_word(dutch, geweest).
+stop_word(dutch, andere).
+
+
+% Man bijt hond specific
+stop_word(dutch, 'man bijt hond').
+stop_word(dutch, man).
+stop_word(dutch, bijt).
+stop_word(dutch, hond).