mirror of
https://github.com/NixOS/nixpkgs.git
synced 2024-12-21 05:25:38 +00:00
42 lines
1.5 KiB
Nix
42 lines
1.5 KiB
Nix
{ 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"; };
|
|
nativeBuildInputs = [ pkgconfig ];
|
|
buildInputs = [ automake autoconf libtool 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.
|
|
'';
|
|
};
|
|
|
|
}
|