blob: 0ba7e686e43463501b96c545a387026607569fc1 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
|
{ stdenv, fetchurl
, automake, autoconf, libtool, pkgconfig, autoconf-archive
, libxml2
, languageMachines
}:
let
release = builtins.fromJSON (builtins.readFile ./release-info/LanguageMachines-mbt.json);
in
stdenv.mkDerivation {
name = "mbt";
version = release.version;
src = fetchurl { inherit (release) url sha256;
name = "mbt-${release.version}.tar.gz"; };
buildInputs = [ automake autoconf libtool pkgconfig autoconf-archive
libxml2
languageMachines.ticcutils
languageMachines.timbl
];
patches = [ ./mbt-add-libxml2-dep.patch ];
preConfigure = ''
sh bootstrap.sh
'';
meta = with stdenv.lib; {
description = "Memory Based Tagger";
homepage = https://languagemachines.github.io/mbt/;
license = licenses.gpl3;
platforms = platforms.all;
maintainers = with maintainers; [ roberth ];
longDescription = ''
MBT is a memory-based tagger-generator and tagger in one. The tagger-generator part can generate a sequence tagger on the basis of a training set of tagged sequences; the tagger part can tag new sequences. MBT can, for instance, be used to generate part-of-speech taggers or chunkers for natural language processing. It has also been used for named-entity recognition, information extraction in domain-specific texts, and disfluency chunking in transcribed speech.
Mbt is used by Frog for Dutch tagging.
'';
};
}
|