From 2bdeb1ab4aef7e2fe5d0ad683716fe68ecef17de Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alexander=20K=C3=B6nig?= Date: Wed, 13 Nov 2024 23:00:55 +0100 Subject: [PATCH] cleaned up pos tools --- tools/pos-and-lemmatisation/abltagger-lem.json | 1 - tools/pos-and-lemmatisation/abltagger-pos.json | 1 - tools/pos-and-lemmatisation/afrikaans-tnt.json | 1 - tools/pos-and-lemmatisation/assamese-pos.json | 1 - tools/pos-and-lemmatisation/char-level-pos-slv.json | 1 - tools/pos-and-lemmatisation/clarin-dk-nlp-toolbox.json | 1 - tools/pos-and-lemmatisation/clark.json | 1 - tools/pos-and-lemmatisation/claws.json | 1 - tools/pos-and-lemmatisation/corpus-by.json | 1 - tools/pos-and-lemmatisation/cst-lemmatizer.json | 1 - tools/pos-and-lemmatisation/estnltk.json | 1 - tools/pos-and-lemmatisation/fintag.json | 1 - tools/pos-and-lemmatisation/freeling.json | 1 - tools/pos-and-lemmatisation/frog.json | 1 - tools/pos-and-lemmatisation/genia-tagger.json | 1 - tools/pos-and-lemmatisation/hmm-tagger.json | 1 - tools/pos-and-lemmatisation/hunpos.json | 1 - tools/pos-and-lemmatisation/icenlp.json | 1 - tools/pos-and-lemmatisation/ilsp-feature.json | 1 - tools/pos-and-lemmatisation/inl-labs.json | 1 - tools/pos-and-lemmatisation/janes-tagger.json | 1 - tools/pos-and-lemmatisation/lem-por.json | 1 - tools/pos-and-lemmatisation/lx-tagger.json | 1 - tools/pos-and-lemmatisation/lx-verbal-lem.json | 1 - tools/pos-and-lemmatisation/mlss.json | 1 - tools/pos-and-lemmatisation/morfeusz2.json | 1 - tools/pos-and-lemmatisation/morphadorner.json | 1 - tools/pos-and-lemmatisation/morphodita-pol.json | 1 - tools/pos-and-lemmatisation/morphodita.json | 1 - tools/pos-and-lemmatisation/nchlt-afr-lem.json | 1 - tools/pos-and-lemmatisation/nchlt-isindebele.json | 1 - tools/pos-and-lemmatisation/nchlt-isizulu.json | 1 - tools/pos-and-lemmatisation/nchlt-sepedi.json | 1 - tools/pos-and-lemmatisation/nchlt-sesotho.json | 1 - tools/pos-and-lemmatisation/nchlt-setswana.json | 1 - tools/pos-and-lemmatisation/nchlt-siswati.json | 1 - tools/pos-and-lemmatisation/nchlt-tagger.json | 1 - tools/pos-and-lemmatisation/nchlt-tshivenda.json | 1 - tools/pos-and-lemmatisation/nchlt-xitsonga.json | 1 - tools/pos-and-lemmatisation/nlp-pipe.json | 1 - tools/pos-and-lemmatisation/opennlp-pos-deu.json | 1 - tools/pos-and-lemmatisation/opennlp-pos-eng.json | 1 - tools/pos-and-lemmatisation/opennlp-pos-por.json | 1 - tools/pos-and-lemmatisation/oslo-bergen.json | 1 - tools/pos-and-lemmatisation/pos-opennlp.json | 1 - tools/pos-and-lemmatisation/reldianno.json | 1 - tools/pos-and-lemmatisation/rftagger.json | 1 - tools/pos-and-lemmatisation/sentione2.json | 1 - tools/pos-and-lemmatisation/sepedi-pos-tagger.json | 1 - tools/pos-and-lemmatisation/sepverb.json | 1 - tools/pos-and-lemmatisation/smor.json | 1 - tools/pos-and-lemmatisation/sparv.json | 3 +-- tools/pos-and-lemmatisation/stanford-dep.json | 1 - tools/pos-and-lemmatisation/stanford-phrase.json | 1 - tools/pos-and-lemmatisation/stepp-tagger.json | 1 - tools/pos-and-lemmatisation/sticker-ud.json | 1 - tools/pos-and-lemmatisation/stuttgart-dep.json | 1 - tools/pos-and-lemmatisation/tadpole.json | 1 - tools/pos-and-lemmatisation/tagger-ws.json | 1 - tools/pos-and-lemmatisation/takipi.json | 1 - tools/pos-and-lemmatisation/template.json | 1 - tools/pos-and-lemmatisation/treetagger.json | 1 - tools/pos-and-lemmatisation/turku-neural.json | 1 - tools/pos-and-lemmatisation/udpipe.json | 1 - tools/pos-and-lemmatisation/vabamorf.json | 1 - tools/pos-and-lemmatisation/wcrft.json | 1 - tools/pos-and-lemmatisation/weblicht-pos.json | 1 - tools/pos-and-lemmatisation/wmbt.json | 1 - 68 files changed, 1 insertion(+), 69 deletions(-) diff --git a/tools/pos-and-lemmatisation/abltagger-lem.json b/tools/pos-and-lemmatisation/abltagger-lem.json index d5ebecf..f1799de 100644 --- a/tools/pos-and-lemmatisation/abltagger-lem.json +++ b/tools/pos-and-lemmatisation/abltagger-lem.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["isl"], "Licence": "The MIT License", - "Platform": [], "Infrastructure": "CLARIN-IS", "Group": "For a single language", "Input format": ["tokenised plain text"], diff --git a/tools/pos-and-lemmatisation/abltagger-pos.json b/tools/pos-and-lemmatisation/abltagger-pos.json index 39e3c8d..adc1913 100644 --- a/tools/pos-and-lemmatisation/abltagger-pos.json +++ b/tools/pos-and-lemmatisation/abltagger-pos.json @@ -6,7 +6,6 @@ "Functionality": ["PoS"], "Language": ["isl"], "Licence": "Apache License 2.0", - "Platform": [], "Infrastructure": "CLARIN-IS", "Group": "For a single language", "Input format": ["tokenised plain or pre-tagged text"], diff --git a/tools/pos-and-lemmatisation/afrikaans-tnt.json b/tools/pos-and-lemmatisation/afrikaans-tnt.json index 2987f45..6c335a8 100644 --- a/tools/pos-and-lemmatisation/afrikaans-tnt.json +++ b/tools/pos-and-lemmatisation/afrikaans-tnt.json @@ -6,7 +6,6 @@ "Functionality": ["PoS"], "Language": ["afr"], "Licence": "research only", - "Platform": [], "Infrastructure": "SADiLaR", "Group": "For a single language", "Input format": ["plain text"], diff --git a/tools/pos-and-lemmatisation/assamese-pos.json b/tools/pos-and-lemmatisation/assamese-pos.json index b60d74e..6951c36 100644 --- a/tools/pos-and-lemmatisation/assamese-pos.json +++ b/tools/pos-and-lemmatisation/assamese-pos.json @@ -6,7 +6,6 @@ "Functionality": ["PoS"], "Language": ["asm"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN-PL", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/char-level-pos-slv.json b/tools/pos-and-lemmatisation/char-level-pos-slv.json index 7204d4f..35e06d4 100644 --- a/tools/pos-and-lemmatisation/char-level-pos-slv.json +++ b/tools/pos-and-lemmatisation/char-level-pos-slv.json @@ -6,7 +6,6 @@ "Functionality": ["PoS"], "Language": ["slv"], "Licence": "GNU General Public Licence, version 3", - "Platform": [], "Infrastructure": "CLARIN.SI", "Group": "For a single language", "Input format": ["XML", "TEI", "plain text"], diff --git a/tools/pos-and-lemmatisation/clarin-dk-nlp-toolbox.json b/tools/pos-and-lemmatisation/clarin-dk-nlp-toolbox.json index a3b88a8..ccd5244 100644 --- a/tools/pos-and-lemmatisation/clarin-dk-nlp-toolbox.json +++ b/tools/pos-and-lemmatisation/clarin-dk-nlp-toolbox.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "lemma", "frequency lists"], "Language": ["dan", "eng"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN-DK", "Group": "For multiple languages", "Input format": ["plain text", "rtf", "pdf"], diff --git a/tools/pos-and-lemmatisation/clark.json b/tools/pos-and-lemmatisation/clark.json index 92a4a12..6730a6f 100644 --- a/tools/pos-and-lemmatisation/clark.json +++ b/tools/pos-and-lemmatisation/clark.json @@ -6,7 +6,6 @@ "Functionality": ["sentence splitting", "PoS", "lemma", "syntactic parsing"], "Language": ["bul"], "Licence": "", - "Platform": [], "Infrastructure": "ClaDA-BG", "Group": "For a single language", "Input format": ["XML"], diff --git a/tools/pos-and-lemmatisation/claws.json b/tools/pos-and-lemmatisation/claws.json index 9505dbb..3f830b2 100644 --- a/tools/pos-and-lemmatisation/claws.json +++ b/tools/pos-and-lemmatisation/claws.json @@ -6,7 +6,6 @@ "Functionality": ["PoS/MSD"], "Language": ["eng"], "Licence": "Terms of Service", - "Platform": [], "Infrastructure": "CLARIN UK", "Group": "For a single language", "Input format": ["plain text"], diff --git a/tools/pos-and-lemmatisation/corpus-by.json b/tools/pos-and-lemmatisation/corpus-by.json index 8d6dcf8..8d0f8ce 100644 --- a/tools/pos-and-lemmatisation/corpus-by.json +++ b/tools/pos-and-lemmatisation/corpus-by.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["bel"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN Knowledge Centre for Belarusian text and speech processing", "Group": "For a single language", "Input format": ["plain text"], diff --git a/tools/pos-and-lemmatisation/cst-lemmatizer.json b/tools/pos-and-lemmatisation/cst-lemmatizer.json index 3ce7de2..43236b9 100644 --- a/tools/pos-and-lemmatisation/cst-lemmatizer.json +++ b/tools/pos-and-lemmatisation/cst-lemmatizer.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["bul", "ces", "dan", "nld", "eng", "est", "fas", "fra", "deu", "ell", "hun", "isl", "ita", "lat", "mkd", "pol", "por", "ron", "rus", "srp", "slk", "slv", "spa", "ukr"], "Licence": "", - "Platform": [], "Infrastructure": "LINDAT/CLARIN-DK", "Group": "For multiple languages", "Input format": [], diff --git a/tools/pos-and-lemmatisation/estnltk.json b/tools/pos-and-lemmatisation/estnltk.json index 1c15b80..08b2dd7 100644 --- a/tools/pos-and-lemmatisation/estnltk.json +++ b/tools/pos-and-lemmatisation/estnltk.json @@ -6,7 +6,6 @@ "Functionality": ["MSD", "NER"], "Language": ["est"], "Licence": "Available - Unrestricted Use", - "Platform": [], "Infrastructure": "CELR", "Group": "For a single language", "Input format": ["plain text"], diff --git a/tools/pos-and-lemmatisation/fintag.json b/tools/pos-and-lemmatisation/fintag.json index fb9f8c2..bdefff2 100644 --- a/tools/pos-and-lemmatisation/fintag.json +++ b/tools/pos-and-lemmatisation/fintag.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "lemma", "NER"], "Language": ["fin"], "Licence": "GPL", - "Platform": [], "Infrastructure": "FIN-CLARIN", "Group": "For a single language", "Input format": ["plain text", "pdf", "doc", "scv", "epub", "html", "odt", "xls"], diff --git a/tools/pos-and-lemmatisation/freeling.json b/tools/pos-and-lemmatisation/freeling.json index d82755d..e56751d 100644 --- a/tools/pos-and-lemmatisation/freeling.json +++ b/tools/pos-and-lemmatisation/freeling.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "lemma"], "Language": ["ita"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN-IT", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/frog.json b/tools/pos-and-lemmatisation/frog.json index 422e986..23a5337 100644 --- a/tools/pos-and-lemmatisation/frog.json +++ b/tools/pos-and-lemmatisation/frog.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "MSD", "lemma", "NE", "phrase chunks", "dependency relations with head words"], "Language": ["nld"], "Licence": "GNU General Public Licence", - "Platform": [], "Infrastructure": "CLARIAH-NL", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/genia-tagger.json b/tools/pos-and-lemmatisation/genia-tagger.json index c3bef99..d6c3552 100644 --- a/tools/pos-and-lemmatisation/genia-tagger.json +++ b/tools/pos-and-lemmatisation/genia-tagger.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "lemma", "chunks", "named entities"], "Language": ["eng", "ces", "slk"], "Licence": "proprietary - commercial", - "Platform": [], "Infrastructure": "PORTULAN", "Group": "For multiple languages", "Input format": [], diff --git a/tools/pos-and-lemmatisation/hmm-tagger.json b/tools/pos-and-lemmatisation/hmm-tagger.json index 70f49de..84bbe43 100644 --- a/tools/pos-and-lemmatisation/hmm-tagger.json +++ b/tools/pos-and-lemmatisation/hmm-tagger.json @@ -6,7 +6,6 @@ "Functionality": ["MSD"], "Language": ["ces"], "Licence": "GNU General Public Licence, version 2", - "Platform": [], "Infrastructure": "LINDAT", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/hunpos.json b/tools/pos-and-lemmatisation/hunpos.json index 4929550..48ae2fe 100644 --- a/tools/pos-and-lemmatisation/hunpos.json +++ b/tools/pos-and-lemmatisation/hunpos.json @@ -6,7 +6,6 @@ "Functionality": ["PoS"], "Language": ["hun"], "Licence": "New BSD License", - "Platform": [], "Infrastructure": "LINDAT", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/icenlp.json b/tools/pos-and-lemmatisation/icenlp.json index 57d16d4..93e9d46 100644 --- a/tools/pos-and-lemmatisation/icenlp.json +++ b/tools/pos-and-lemmatisation/icenlp.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "lemma", "shallow syntactic parsing"], "Language": ["isl"], "Licence": "GNU General Public License, version 2", - "Platform": [], "Infrastructure": "CLARIN-IS", "Group": "For a single language", "Input format": ["plain text"], diff --git a/tools/pos-and-lemmatisation/ilsp-feature.json b/tools/pos-and-lemmatisation/ilsp-feature.json index c7fa26f..66229d0 100644 --- a/tools/pos-and-lemmatisation/ilsp-feature.json +++ b/tools/pos-and-lemmatisation/ilsp-feature.json @@ -6,7 +6,6 @@ "Functionality": ["PoS"], "Language": ["ell"], "Licence": "terms of service (Restrictions: Academic - Non Commercial Use)", - "Platform": [], "Infrastructure": "CLARIN:EL", "Group": "For a single language", "Input format": ["Application/vnd.xmi+xml"], diff --git a/tools/pos-and-lemmatisation/inl-labs.json b/tools/pos-and-lemmatisation/inl-labs.json index bfa0808..f773cfe 100644 --- a/tools/pos-and-lemmatisation/inl-labs.json +++ b/tools/pos-and-lemmatisation/inl-labs.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "lemma"], "Language": ["nld"], "Licence": "CLARIN PUB", - "Platform": [], "Infrastructure": "CLARIAH-NL", "Group": "For a single language", "Input format": ["plain text", "TEI", "epub", "html", "docx", "alto"], diff --git a/tools/pos-and-lemmatisation/janes-tagger.json b/tools/pos-and-lemmatisation/janes-tagger.json index 4c3fbb8..b8a6caf 100644 --- a/tools/pos-and-lemmatisation/janes-tagger.json +++ b/tools/pos-and-lemmatisation/janes-tagger.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "lemma"], "Language": ["slv"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN.SI", "Group": "For a single language", "Input format": ["plain text"], diff --git a/tools/pos-and-lemmatisation/lem-por.json b/tools/pos-and-lemmatisation/lem-por.json index ff8a655..bc21f5b 100644 --- a/tools/pos-and-lemmatisation/lem-por.json +++ b/tools/pos-and-lemmatisation/lem-por.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["por"], "Licence": "Apache Licence 2.0 (academic)", - "Platform": [], "Infrastructure": "PORTULAN", "Group": "For a single language", "Input format": ["plain text"], diff --git a/tools/pos-and-lemmatisation/lx-tagger.json b/tools/pos-and-lemmatisation/lx-tagger.json index 041b03b..8b93ca2 100644 --- a/tools/pos-and-lemmatisation/lx-tagger.json +++ b/tools/pos-and-lemmatisation/lx-tagger.json @@ -6,7 +6,6 @@ "Functionality": ["MSD"], "Language": ["por"], "Licence": "Academic - Non-Commercial use", - "Platform": [], "Infrastructure": "PORTULAN", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/lx-verbal-lem.json b/tools/pos-and-lemmatisation/lx-verbal-lem.json index 4d6962f..3264e50 100644 --- a/tools/pos-and-lemmatisation/lx-verbal-lem.json +++ b/tools/pos-and-lemmatisation/lx-verbal-lem.json @@ -6,7 +6,6 @@ "Functionality": ["lemma (verbs)"], "Language": ["por"], "Licence": "Terms of Service", - "Platform": [], "Infrastructure": "PORTULAN", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/mlss.json b/tools/pos-and-lemmatisation/mlss.json index 491924f..84e6f82 100644 --- a/tools/pos-and-lemmatisation/mlss.json +++ b/tools/pos-and-lemmatisation/mlss.json @@ -6,7 +6,6 @@ "Functionality": ["PoS"], "Language": ["mlt"], "Licence": "CLARIN ACA", - "Platform": [], "Infrastructure": "PORTULAN", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/morfeusz2.json b/tools/pos-and-lemmatisation/morfeusz2.json index b73bfe9..7deb015 100644 --- a/tools/pos-and-lemmatisation/morfeusz2.json +++ b/tools/pos-and-lemmatisation/morfeusz2.json @@ -6,7 +6,6 @@ "Functionality": ["MSD"], "Language": ["pol"], "Licence": "BSD 2 (public)", - "Platform": [], "Infrastructure": "CLARIN-PL", "Group": "For a single language", "Input format": ["various"], diff --git a/tools/pos-and-lemmatisation/morphadorner.json b/tools/pos-and-lemmatisation/morphadorner.json index 50c00cd..5180ff2 100644 --- a/tools/pos-and-lemmatisation/morphadorner.json +++ b/tools/pos-and-lemmatisation/morphadorner.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["eng"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN-D", "Group": "For a single language", "Input format": ["TCF", "XML"], diff --git a/tools/pos-and-lemmatisation/morphodita-pol.json b/tools/pos-and-lemmatisation/morphodita-pol.json index 3a7752d..a7140ea 100644 --- a/tools/pos-and-lemmatisation/morphodita-pol.json +++ b/tools/pos-and-lemmatisation/morphodita-pol.json @@ -6,7 +6,6 @@ "Functionality": ["MSD"], "Language": ["pol"], "Licence": "GNU LGPL 3.0", - "Platform": [], "Infrastructure": "CLARIN-PL", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/morphodita.json b/tools/pos-and-lemmatisation/morphodita.json index 3d0cb3d..9a69a8a 100644 --- a/tools/pos-and-lemmatisation/morphodita.json +++ b/tools/pos-and-lemmatisation/morphodita.json @@ -6,7 +6,6 @@ "Functionality": ["MSD", "lemma"], "Language": ["eng", "ces", "slk"], "Licence": "Mozilla Public Licence 2.0 (software); CC BY-NC-SA (models)", - "Platform": [], "Infrastructure": "LINDAT", "Group": "For multiple languages", "Input format": ["plain text", "vertical"], diff --git a/tools/pos-and-lemmatisation/nchlt-afr-lem.json b/tools/pos-and-lemmatisation/nchlt-afr-lem.json index 40814d3..a786690 100644 --- a/tools/pos-and-lemmatisation/nchlt-afr-lem.json +++ b/tools/pos-and-lemmatisation/nchlt-afr-lem.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["afr"], "Licence": "CC-BY 2.5 South Africa Licence", - "Platform": [], "Infrastructure": "SADiLaR", "Group": "For a single language", "Input format": ["Text data (encoding: UTF8 without BOM), one lowercase token per line"], diff --git a/tools/pos-and-lemmatisation/nchlt-isindebele.json b/tools/pos-and-lemmatisation/nchlt-isindebele.json index cf5299b..0e93b89 100644 --- a/tools/pos-and-lemmatisation/nchlt-isindebele.json +++ b/tools/pos-and-lemmatisation/nchlt-isindebele.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["Ndebele"], "Licence": "CC-BY 2.5 South Africa Licence", - "Platform": [], "Infrastructure": "SADiLaR", "Group": "For a single language", "Input format": ["Text data (encoding: UTF8 without BOM), one lowercase token per line"], diff --git a/tools/pos-and-lemmatisation/nchlt-isizulu.json b/tools/pos-and-lemmatisation/nchlt-isizulu.json index bcfba70..5cf72ce 100644 --- a/tools/pos-and-lemmatisation/nchlt-isizulu.json +++ b/tools/pos-and-lemmatisation/nchlt-isizulu.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["Zulu"], "Licence": "CC-BY 2.5 South Africa Licence", - "Platform": [], "Infrastructure": "SADiLaR", "Group": "For a single language", "Input format": ["Text data (encoding: UTF8 without BOM), one lowercase token per line"], diff --git a/tools/pos-and-lemmatisation/nchlt-sepedi.json b/tools/pos-and-lemmatisation/nchlt-sepedi.json index 042bfb0..599287a 100644 --- a/tools/pos-and-lemmatisation/nchlt-sepedi.json +++ b/tools/pos-and-lemmatisation/nchlt-sepedi.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["Sepedi"], "Licence": "CC-BY 2.5 South Africa Licence", - "Platform": [], "Infrastructure": "SADiLaR", "Group": "For a single language", "Input format": ["Text data (encoding: UTF8 without BOM), one lowercase token per line"], diff --git a/tools/pos-and-lemmatisation/nchlt-sesotho.json b/tools/pos-and-lemmatisation/nchlt-sesotho.json index 50d6a59..345daa1 100644 --- a/tools/pos-and-lemmatisation/nchlt-sesotho.json +++ b/tools/pos-and-lemmatisation/nchlt-sesotho.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["Sesotho"], "Licence": "CC-BY 2.5 South Africa Licence", - "Platform": [], "Infrastructure": "SADiLaR", "Group": "For a single language", "Input format": ["Text data (encoding: UTF8 without BOM), one lowercase token per line"], diff --git a/tools/pos-and-lemmatisation/nchlt-setswana.json b/tools/pos-and-lemmatisation/nchlt-setswana.json index bacaffb..4b67522 100644 --- a/tools/pos-and-lemmatisation/nchlt-setswana.json +++ b/tools/pos-and-lemmatisation/nchlt-setswana.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["Tswana"], "Licence": "CC-BY 2.5 South Africa Licence", - "Platform": [], "Infrastructure": "SADiLaR", "Group": "For a single language", "Input format": ["Text data (encoding: UTF8 without BOM), one lowercase token per line"], diff --git a/tools/pos-and-lemmatisation/nchlt-siswati.json b/tools/pos-and-lemmatisation/nchlt-siswati.json index 268fb83..4a20bb2 100644 --- a/tools/pos-and-lemmatisation/nchlt-siswati.json +++ b/tools/pos-and-lemmatisation/nchlt-siswati.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["Swazi"], "Licence": "CC-BY 2.5 South Africa Licence", - "Platform": [], "Infrastructure": "SADiLaR", "Group": "For a single language", "Input format": ["Text data (encoding: UTF8 without BOM), one lowercase token per line"], diff --git a/tools/pos-and-lemmatisation/nchlt-tagger.json b/tools/pos-and-lemmatisation/nchlt-tagger.json index e23c416..f07d843 100644 --- a/tools/pos-and-lemmatisation/nchlt-tagger.json +++ b/tools/pos-and-lemmatisation/nchlt-tagger.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "phrase chunks", "NE"], "Language": ["afr", "eng", "Ndebele", "xho", "zul", "Sesotho sa Leboa", "tsn", "Sesotho", "ssw", "ven", "tso"], "Licence": "CC-BY 2.5 South Africa Licence", - "Platform": [], "Infrastructure": "SADiLaR", "Group": "For multiple languages", "Input format": ["Utf8 text file containing running text"], diff --git a/tools/pos-and-lemmatisation/nchlt-tshivenda.json b/tools/pos-and-lemmatisation/nchlt-tshivenda.json index 82133fb..33678aa 100644 --- a/tools/pos-and-lemmatisation/nchlt-tshivenda.json +++ b/tools/pos-and-lemmatisation/nchlt-tshivenda.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["Venda"], "Licence": "CC-BY 2.5 South Africa Licence", - "Platform": [], "Infrastructure": "SADiLaR", "Group": "For a single language", "Input format": ["Text data (encoding: UTF8 without BOM), one lowercase token per line"], diff --git a/tools/pos-and-lemmatisation/nchlt-xitsonga.json b/tools/pos-and-lemmatisation/nchlt-xitsonga.json index 88a2569..d8d1560 100644 --- a/tools/pos-and-lemmatisation/nchlt-xitsonga.json +++ b/tools/pos-and-lemmatisation/nchlt-xitsonga.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["Tsonga"], "Licence": "CC-BY 2.5 South Africa Licence", - "Platform": [], "Infrastructure": "SADiLaR", "Group": "For a single language", "Input format": ["Text data (encoding: UTF8 without BOM), one lowercase token per line"], diff --git a/tools/pos-and-lemmatisation/nlp-pipe.json b/tools/pos-and-lemmatisation/nlp-pipe.json index ca1a6cf..99884a5 100644 --- a/tools/pos-and-lemmatisation/nlp-pipe.json +++ b/tools/pos-and-lemmatisation/nlp-pipe.json @@ -6,7 +6,6 @@ "Functionality": ["MSD", "syntactic parsing", "NER"], "Language": ["lav"], "Licence": "GNU General Public Licence 3", - "Platform": [], "Infrastructure": "CLARIN-LV", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/opennlp-pos-deu.json b/tools/pos-and-lemmatisation/opennlp-pos-deu.json index e24d7e5..5ef6bc4 100644 --- a/tools/pos-and-lemmatisation/opennlp-pos-deu.json +++ b/tools/pos-and-lemmatisation/opennlp-pos-deu.json @@ -6,7 +6,6 @@ "Functionality": ["PoS"], "Language": ["deu"], "Licence": "Apache Licence 2.0 (restricted)", - "Platform": [], "Infrastructure": "CLARIN:EL", "Group": "For a single language", "Input format": ["application/xml"], diff --git a/tools/pos-and-lemmatisation/opennlp-pos-eng.json b/tools/pos-and-lemmatisation/opennlp-pos-eng.json index 2e43646..bb711eb 100644 --- a/tools/pos-and-lemmatisation/opennlp-pos-eng.json +++ b/tools/pos-and-lemmatisation/opennlp-pos-eng.json @@ -6,7 +6,6 @@ "Functionality": ["PoS"], "Language": ["eng"], "Licence": "Apache Licence 2.0 (restricted)", - "Platform": [], "Infrastructure": "CLARIN:EL", "Group": "For a single language", "Input format": ["application/xml"], diff --git a/tools/pos-and-lemmatisation/opennlp-pos-por.json b/tools/pos-and-lemmatisation/opennlp-pos-por.json index 991bb6e..6bb59d6 100644 --- a/tools/pos-and-lemmatisation/opennlp-pos-por.json +++ b/tools/pos-and-lemmatisation/opennlp-pos-por.json @@ -6,7 +6,6 @@ "Functionality": ["PoS"], "Language": ["por"], "Licence": "Apache Licence 2.0 (restricted)", - "Platform": [], "Infrastructure": "CLARIN:EL", "Group": "For a single language", "Input format": ["application/xml"], diff --git a/tools/pos-and-lemmatisation/oslo-bergen.json b/tools/pos-and-lemmatisation/oslo-bergen.json index b383455..a460467 100644 --- a/tools/pos-and-lemmatisation/oslo-bergen.json +++ b/tools/pos-and-lemmatisation/oslo-bergen.json @@ -6,7 +6,6 @@ "Functionality": ["MSD", "syntactic parsing"], "Language": ["Norwegian (Bokmål and Nynorsk)"], "Licence": "GNU General public licence", - "Platform": [], "Infrastructure": "CLARINO", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/pos-opennlp.json b/tools/pos-and-lemmatisation/pos-opennlp.json index c56f26a..e7df06a 100644 --- a/tools/pos-and-lemmatisation/pos-opennlp.json +++ b/tools/pos-and-lemmatisation/pos-opennlp.json @@ -6,7 +6,6 @@ "Functionality": ["PoS"], "Language": ["deu", "eng", "ita"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN-D", "Group": "For multiple languages", "Input format": ["TCF", "XML"], diff --git a/tools/pos-and-lemmatisation/reldianno.json b/tools/pos-and-lemmatisation/reldianno.json index 8057de5..79c208e 100644 --- a/tools/pos-and-lemmatisation/reldianno.json +++ b/tools/pos-and-lemmatisation/reldianno.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "lemma", "NER", "syntactic parsing"], "Language": ["hrv", "srp", "slv"], "Licence": "CC-BY (for webservice); Apache 2 for library", - "Platform": [], "Infrastructure": "CLARIN.SI", "Group": "For multiple languages", "Input format": ["plain text", "TCF"], diff --git a/tools/pos-and-lemmatisation/rftagger.json b/tools/pos-and-lemmatisation/rftagger.json index c9649cd..32d0f33 100644 --- a/tools/pos-and-lemmatisation/rftagger.json +++ b/tools/pos-and-lemmatisation/rftagger.json @@ -6,7 +6,6 @@ "Functionality": ["PoS"], "Language": ["deu", "ces", "slv", "hun"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN-D", "Group": "For multiple languages", "Input format": [], diff --git a/tools/pos-and-lemmatisation/sentione2.json b/tools/pos-and-lemmatisation/sentione2.json index d95bb8b..0d43a02 100644 --- a/tools/pos-and-lemmatisation/sentione2.json +++ b/tools/pos-and-lemmatisation/sentione2.json @@ -6,7 +6,6 @@ "Functionality": ["MSD"], "Language": ["pol"], "Licence": "GNU GPL3", - "Platform": [], "Infrastructure": "CLARIN-PL", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/sepedi-pos-tagger.json b/tools/pos-and-lemmatisation/sepedi-pos-tagger.json index 721d4ee..0ec5134 100644 --- a/tools/pos-and-lemmatisation/sepedi-pos-tagger.json +++ b/tools/pos-and-lemmatisation/sepedi-pos-tagger.json @@ -6,7 +6,6 @@ "Functionality": ["PoS"], "Language": ["Sepedi"], "Licence": "", - "Platform": [], "Infrastructure": "SADiLaR", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/sepverb.json b/tools/pos-and-lemmatisation/sepverb.json index ed9b4a8..5fdabb9 100644 --- a/tools/pos-and-lemmatisation/sepverb.json +++ b/tools/pos-and-lemmatisation/sepverb.json @@ -6,7 +6,6 @@ "Functionality": ["lemma"], "Language": ["deu"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN-D", "Group": "For a single language", "Input format": ["TCF", "XML"], diff --git a/tools/pos-and-lemmatisation/smor.json b/tools/pos-and-lemmatisation/smor.json index 056fff2..1f5aee8 100644 --- a/tools/pos-and-lemmatisation/smor.json +++ b/tools/pos-and-lemmatisation/smor.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "lemma"], "Language": ["deu"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN-D", "Group": "For a single language", "Input format": ["TCF", "XML"], diff --git a/tools/pos-and-lemmatisation/sparv.json b/tools/pos-and-lemmatisation/sparv.json index 6120fb0..27d03f4 100644 --- a/tools/pos-and-lemmatisation/sparv.json +++ b/tools/pos-and-lemmatisation/sparv.json @@ -4,9 +4,8 @@ "Family": "Part-of-Speech Tagging and Lemmatisation", "Description": "This tool is Språkbanken's corpus annotation pipeline infrastructure. The pipeline uses in-house and external tools on the text to segment it into sentences and paragraphs, tokenise, tag parts-of-speech, look up in dictionaries and analyse compounds. The pipeline can also be run using a web API with XML results, and it is run locally to prepare the documents in Korp, which is SWE-LANG’s corpus search tool. While the most sophisticated support is for modern Swedish, the pipeline supports additional 19 languages.", "Functionality": ["PoS", "MSD", "lemma", "compound analysis", "dictionary lookup"], - "Language": ["Bulgarian, English, Estonian, Finnish, French, Galician, Italian, Catalan, Latin, Dutch, Norwegian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, German"], + "Language": ["bul", "eng", "est", "fin", "fra", "glg", "ita", "cat", "lat", "nld", "nor", "pol", "por", "ron", "rus", "slk", "slv", "spa", "swe", "deu"], "Licence": "", - "Platform": [], "Infrastructure": "SWE-CLARIN", "Group": "For multiple languages", "Input format": ["plain text", "XML"], diff --git a/tools/pos-and-lemmatisation/stanford-dep.json b/tools/pos-and-lemmatisation/stanford-dep.json index e4a132f..eed84a6 100644 --- a/tools/pos-and-lemmatisation/stanford-dep.json +++ b/tools/pos-and-lemmatisation/stanford-dep.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "syntactic parsing"], "Language": ["eng"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN-D", "Group": "For a single language", "Input format": ["plain text", "pdf", "rtf", "XML"], diff --git a/tools/pos-and-lemmatisation/stanford-phrase.json b/tools/pos-and-lemmatisation/stanford-phrase.json index c1ec46d..01ab877 100644 --- a/tools/pos-and-lemmatisation/stanford-phrase.json +++ b/tools/pos-and-lemmatisation/stanford-phrase.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "syntactic parsing"], "Language": ["eng", "deu"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN-D", "Group": "For multiple languages", "Input format": ["plain text", "pdf", "rtf", "XML"], diff --git a/tools/pos-and-lemmatisation/stepp-tagger.json b/tools/pos-and-lemmatisation/stepp-tagger.json index 85916c6..ca531f2 100644 --- a/tools/pos-and-lemmatisation/stepp-tagger.json +++ b/tools/pos-and-lemmatisation/stepp-tagger.json @@ -6,7 +6,6 @@ "Functionality": ["PoS"], "Language": ["eng", "ces", "slk"], "Licence": "proprietary - commercial", - "Platform": [], "Infrastructure": "PORTULAN", "Group": "For multiple languages", "Input format": ["plain text"], diff --git a/tools/pos-and-lemmatisation/sticker-ud.json b/tools/pos-and-lemmatisation/sticker-ud.json index 1c11f48..b51ac2d 100644 --- a/tools/pos-and-lemmatisation/sticker-ud.json +++ b/tools/pos-and-lemmatisation/sticker-ud.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "syntactic parsing", "NER"], "Language": ["deu", "nld"], "Licence": "Blue Oak Mode Licence version 1.0.0", - "Platform": [], "Infrastructure": "CLARIN-D", "Group": "For multiple languages", "Input format": [], diff --git a/tools/pos-and-lemmatisation/stuttgart-dep.json b/tools/pos-and-lemmatisation/stuttgart-dep.json index bf2c106..25a328f 100644 --- a/tools/pos-and-lemmatisation/stuttgart-dep.json +++ b/tools/pos-and-lemmatisation/stuttgart-dep.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "syntactic parsing"], "Language": ["deu"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN-D", "Group": "For a single language", "Input format": ["plain text", "pdf", "rtf", "XML"], diff --git a/tools/pos-and-lemmatisation/tadpole.json b/tools/pos-and-lemmatisation/tadpole.json index 1214b86..5d7843a 100644 --- a/tools/pos-and-lemmatisation/tadpole.json +++ b/tools/pos-and-lemmatisation/tadpole.json @@ -6,7 +6,6 @@ "Functionality": ["PoS/MSD", "lemma", "syntactic parsing"], "Language": ["nld"], "Licence": "", - "Platform": [], "Infrastructure": "LINDAT/CLARIAH-CZ", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/tagger-ws.json b/tools/pos-and-lemmatisation/tagger-ws.json index 2280a48..45b93a3 100644 --- a/tools/pos-and-lemmatisation/tagger-ws.json +++ b/tools/pos-and-lemmatisation/tagger-ws.json @@ -6,7 +6,6 @@ "Functionality": ["MSD", "lemma"], "Language": ["pol"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN-PL", "Group": "For a single language", "Input format": ["plain text", "XML"], diff --git a/tools/pos-and-lemmatisation/takipi.json b/tools/pos-and-lemmatisation/takipi.json index f31636a..d186965 100644 --- a/tools/pos-and-lemmatisation/takipi.json +++ b/tools/pos-and-lemmatisation/takipi.json @@ -6,7 +6,6 @@ "Functionality": ["MSD"], "Language": ["pol"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN-PL", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/template.json b/tools/pos-and-lemmatisation/template.json index bf6c5d7..a62b396 100644 --- a/tools/pos-and-lemmatisation/template.json +++ b/tools/pos-and-lemmatisation/template.json @@ -6,7 +6,6 @@ "Functionality": [], "Language": [], "Licence": "", - "Platform": [], "Infrastructure": "", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/treetagger.json b/tools/pos-and-lemmatisation/treetagger.json index ff518c8..bb4bad1 100644 --- a/tools/pos-and-lemmatisation/treetagger.json +++ b/tools/pos-and-lemmatisation/treetagger.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "lemma"], "Language": ["deu", "eng", "fra", "ita", "nld", "spa", "bul", "rus", "ell", "por", "zho", "swh", "lat", "est", "fro"], "Licence": "free but unspecified", - "Platform": [], "Infrastructure": "CLARIN-D", "Group": "For multiple languages", "Input format": [], diff --git a/tools/pos-and-lemmatisation/turku-neural.json b/tools/pos-and-lemmatisation/turku-neural.json index 75aaa2c..51b2b71 100644 --- a/tools/pos-and-lemmatisation/turku-neural.json +++ b/tools/pos-and-lemmatisation/turku-neural.json @@ -6,7 +6,6 @@ "Functionality": ["segmentation", "MSD", "syntactic parsing", "lemma"], "Language": ["More than 50 languages"], "Licence": "Apache License 2.0", - "Platform": [], "Infrastructure": "FIN-CLARIN", "Group": "For multiple languages", "Input format": ["utf-8 encoded plain text"], diff --git a/tools/pos-and-lemmatisation/udpipe.json b/tools/pos-and-lemmatisation/udpipe.json index 0dcc107..4dc5f22 100644 --- a/tools/pos-and-lemmatisation/udpipe.json +++ b/tools/pos-and-lemmatisation/udpipe.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "lemma", "syntactic parsing"], "Language": ["Language independent"], "Licence": "Mozilla Public Licence 2.0 (software); CC BY-NC-SA UD (models)", - "Platform": [], "Infrastructure": "LINDAT", "Group": "For multiple languages", "Input format": ["plain text"], diff --git a/tools/pos-and-lemmatisation/vabamorf.json b/tools/pos-and-lemmatisation/vabamorf.json index 15f2ca4..a060d43 100644 --- a/tools/pos-and-lemmatisation/vabamorf.json +++ b/tools/pos-and-lemmatisation/vabamorf.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "MSD", "lemma"], "Language": ["est"], "Licence": "Available - Unrestricted Use", - "Platform": [], "Infrastructure": "CELR", "Group": "For a single language", "Input format": ["plain text"], diff --git a/tools/pos-and-lemmatisation/wcrft.json b/tools/pos-and-lemmatisation/wcrft.json index 028c2ce..cdca30f 100644 --- a/tools/pos-and-lemmatisation/wcrft.json +++ b/tools/pos-and-lemmatisation/wcrft.json @@ -6,7 +6,6 @@ "Functionality": ["MSD"], "Language": ["pol"], "Licence": "GNU LGPL 3.0", - "Platform": [], "Infrastructure": "CLARIN-PL", "Group": "For a single language", "Input format": [], diff --git a/tools/pos-and-lemmatisation/weblicht-pos.json b/tools/pos-and-lemmatisation/weblicht-pos.json index 8725b21..62e0461 100644 --- a/tools/pos-and-lemmatisation/weblicht-pos.json +++ b/tools/pos-and-lemmatisation/weblicht-pos.json @@ -6,7 +6,6 @@ "Functionality": ["PoS", "lemma"], "Language": ["deu"], "Licence": "", - "Platform": [], "Infrastructure": "CLARIN-D", "Group": "For a single language", "Input format": ["TCF", "XML"], diff --git a/tools/pos-and-lemmatisation/wmbt.json b/tools/pos-and-lemmatisation/wmbt.json index 3c59b6d..b19a646 100644 --- a/tools/pos-and-lemmatisation/wmbt.json +++ b/tools/pos-and-lemmatisation/wmbt.json @@ -6,7 +6,6 @@ "Functionality": ["MSD"], "Language": ["pol"], "Licence": "GNU LGPL 3.0", - "Platform": [], "Infrastructure": "CLARIN-PL", "Group": "For a single language", "Input format": ["various, default is XCES XML"],