2021-02-05 17:12:51 +00:00
|
|
|
{ lib, stdenv, fetchurl
|
|
|
|
|
, automake, autoconf, bzip2, libtar, libtool, pkg-config, autoconf-archive
|
2020-04-24 23:36:52 +00:00
|
|
|
, libxml2
|
|
|
|
|
, languageMachines
|
|
|
|
|
}:
|
|
|
|
|
|
|
|
|
|
let
|
2021-12-06 16:07:01 +00:00
|
|
|
release = lib.importJSON ./release-info/LanguageMachines-mbt.json;
|
2020-04-24 23:36:52 +00:00
|
|
|
in
|
|
|
|
|
|
|
|
|
|
stdenv.mkDerivation {
|
|
|
|
|
name = "mbt-${release.version}";
|
|
|
|
|
version = release.version;
|
|
|
|
|
src = fetchurl { inherit (release) url sha256;
|
|
|
|
|
name = "mbt-${release.version}.tar.gz"; };
|
2022-04-03 18:54:34 +00:00
|
|
|
nativeBuildInputs = [ pkg-config automake autoconf ];
|
|
|
|
|
buildInputs = [ bzip2 libtar libtool autoconf-archive
|
2020-04-24 23:36:52 +00:00
|
|
|
libxml2
|
|
|
|
|
languageMachines.ticcutils
|
|
|
|
|
languageMachines.timbl
|
|
|
|
|
];
|
|
|
|
|
patches = [ ./mbt-add-libxml2-dep.patch ];
|
|
|
|
|
preConfigure = ''
|
|
|
|
|
sh bootstrap.sh
|
|
|
|
|
'';
|
|
|
|
|
|
2021-02-05 17:12:51 +00:00
|
|
|
meta = with lib; {
|
2020-04-24 23:36:52 +00:00
|
|
|
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.
|
|
|
|
|
'';
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
}
|
