From 3595f908f024d3b9c84bc8c2f5eff92407998d85 Mon Sep 17 00:00:00 2001 From: jakoble <37188634+jakoble@users.noreply.github.com> Date: Mon, 28 Oct 2024 12:33:04 +0100 Subject: [PATCH] Add files via upload --- .../affect-in-tweets.json | 16 ++++++++++++++++ .../manually-annotated-corpora/deepbankpt.json | 16 ++++++++++++++++ .../dependency-bank-pt.json | 16 ++++++++++++++++ .../logical-form-bank-pt.json | 16 ++++++++++++++++ .../manual-for-teaching.json | 16 ++++++++++++++++ .../manually-annotated-corpora/propbankpt.json | 16 ++++++++++++++++ .../manually-annotated-corpora/treebank-pt.json | 16 ++++++++++++++++ 7 files changed, 112 insertions(+) create mode 100644 corpora/manually-annotated-corpora/affect-in-tweets.json create mode 100644 corpora/manually-annotated-corpora/deepbankpt.json create mode 100644 corpora/manually-annotated-corpora/dependency-bank-pt.json create mode 100644 corpora/manually-annotated-corpora/logical-form-bank-pt.json create mode 100644 corpora/manually-annotated-corpora/manual-for-teaching.json create mode 100644 corpora/manually-annotated-corpora/propbankpt.json create mode 100644 corpora/manually-annotated-corpora/treebank-pt.json diff --git a/corpora/manually-annotated-corpora/affect-in-tweets.json b/corpora/manually-annotated-corpora/affect-in-tweets.json new file mode 100644 index 0000000..fa537f2 --- /dev/null +++ b/corpora/manually-annotated-corpora/affect-in-tweets.json @@ -0,0 +1,16 @@ +{ + "Name": "Affect in Tweets PT", + "URL": "https://hdl.handle.net/21.11129/0000-000E-75BA-D", + "Family": "Manually annotated corpora", + "Description": "This is a data set of Portuguese tweets labelled with the emotion conveyed in the tweet.\nEach tweet is labelled with an emotion (i.e., anger, fear, joy, sadness).\nThe corpus is available from PORTULAN.", + "Language": ["por"], + "Licence": "CC BY", + "Size": ["11,219 tweets"], + "Annotation": ["sentiment analysis"], + "Infrastructure": "CLARIN", + "Group": ["Sentiment analysis"], + "Access": { + "Download": "https://hdl.handle.net/21.11129/0000-000E-75BA-D" + }, + "Publication": "" +} \ No newline at end of file diff --git a/corpora/manually-annotated-corpora/deepbankpt.json b/corpora/manually-annotated-corpora/deepbankpt.json new file mode 100644 index 0000000..e94bba4 --- /dev/null +++ b/corpora/manually-annotated-corpora/deepbankpt.json @@ -0,0 +1,16 @@ +{ + "Name": "DeepBankPT", + "URL": "https://hdl.handle.net/21.11129/0000-000B-D350-C", + "Family": "Manually annotated corpora", + "Description": "This is a corpus of grammatical analyses conforming to the Head Driven Phrase Structure Grammar framework.\nThe sentences are translations from the Wall Street Journal.\nThe corpus is available from PORTULAN.", + "Language": ["por"], + "Licence": "CC BY", + "Size": ["3,406 sentences", "44,598 tokens"], + "Annotation": ["grammatical structure"], + "Infrastructure": "CLARIN", + "Group": ["Syntactic parsing"], + "Access": { + "Download": "https://hdl.handle.net/21.11129/0000-000B-D350-C" + }, + "Publication": "" +} \ No newline at end of file diff --git a/corpora/manually-annotated-corpora/dependency-bank-pt.json b/corpora/manually-annotated-corpora/dependency-bank-pt.json new file mode 100644 index 0000000..ddffc16 --- /dev/null +++ b/corpora/manually-annotated-corpora/dependency-bank-pt.json @@ -0,0 +1,16 @@ +{ + "Name": "DependencyBankPT", + "URL": "https://hdl.handle.net/21.11129/0000-000B-D34C-2", + "Family": "Manually annotated corpora", + "Description": "This is a corpus of syntactic dependencies.\nThe sentences are translations from the Wall Street Journal.\nThe corpus is available from PORTULAN.", + "Language": ["por"], + "Licence": "CC BY", + "Size": ["3,406 sentences", "44,598 tokens"], + "Annotation": ["grammatical structure"], + "Infrastructure": "CLARIN", + "Group": ["Syntactic parsing"], + "Access": { + "Download": "https://hdl.handle.net/21.11129/0000-000B-D34C-2" + }, + "Publication": "" +} \ No newline at end of file diff --git a/corpora/manually-annotated-corpora/logical-form-bank-pt.json b/corpora/manually-annotated-corpora/logical-form-bank-pt.json new file mode 100644 index 0000000..b0125ae --- /dev/null +++ b/corpora/manually-annotated-corpora/logical-form-bank-pt.json @@ -0,0 +1,16 @@ +{ + "Name": "LogicalFormBankPT", + "URL": "https://hdl.handle.net/21.11129/0000-000B-D34E-0", + "Family": "Manually annotated corpora", + "Description": "This is a corpus of sentences annotated with logical forms. The sentences are translations from the Wall Street Journal.\nThe corpus is available from PORTULAN.", + "Language": ["por"], + "Licence": "CC BY", + "Size": ["3,406 sentences", "44,598 tokens"], + "Annotation": ["Semantic tags"], + "Infrastructure": "CLARIN", + "Group": ["Other annotation layers"], + "Access": { + "Download": "https://hdl.handle.net/21.11129/0000-000B-D34E-0" + }, + "Publication": "" +} \ No newline at end of file diff --git a/corpora/manually-annotated-corpora/manual-for-teaching.json b/corpora/manually-annotated-corpora/manual-for-teaching.json new file mode 100644 index 0000000..2066dfd --- /dev/null +++ b/corpora/manually-annotated-corpora/manual-for-teaching.json @@ -0,0 +1,16 @@ +{ + "Name": "Manually annotated corpora for teaching and learning purposes of Brazilian Portuguese, Dutch, Estonian, and Slovene", + "URL": "https://hdl.handle.net/21.11129/0000-0010-05DA-3 ", + "Family": "Manually annotated corpora", + "Description": "These are manually annotated corpora for teaching and learning purposes of Brazilian Portuguese, Dutch, Estonian, and Slovene.\nSentences are annotated with “problematic” or “non-problematic” labels, from the point of usage for pedagogical purposes.\nThe corpus is available from PORTULAN.", + "Language": ["est", "nld", "slv", "por"], + "Licence": "CC BY", + "Size": ["10,000 sentences"], + "Annotation": ["error tagging"], + "Infrastructure": "CLARIN", + "Group": ["Other annotation layers"], + "Access": { + "Download": "https://hdl.handle.net/21.11129/0000-0010-05DA-3" + }, + "Publication": "" +} \ No newline at end of file diff --git a/corpora/manually-annotated-corpora/propbankpt.json b/corpora/manually-annotated-corpora/propbankpt.json new file mode 100644 index 0000000..f1741de --- /dev/null +++ b/corpora/manually-annotated-corpora/propbankpt.json @@ -0,0 +1,16 @@ +{ + "Name": "PropBankPT", + "URL": "https://hdl.handle.net/21.11129/0000-000B-D34B-3", + "Family": "Manually annotated corpora", + "Description": "This is a corpus of sentences annotated with their constituency structure and semantic role tags. The sentences are translations from the Wall Street Journal.\nThe corpus is available from PORTULAN.", + "Language": ["por"], + "Licence": "CC BY", + "Size": ["3,406 sentences", "44,598 tokens"], + "Annotation": ["Syntactic parsing", "Semantic role tags"], + "Infrastructure": "CLARIN", + "Group": ["Syntactic parsing", "Other annotation layers"], + "Access": { + "Download": "https://hdl.handle.net/21.11129/0000-000B-D34B-3" + }, + "Publication":"" +} \ No newline at end of file diff --git a/corpora/manually-annotated-corpora/treebank-pt.json b/corpora/manually-annotated-corpora/treebank-pt.json new file mode 100644 index 0000000..e4c992d --- /dev/null +++ b/corpora/manually-annotated-corpora/treebank-pt.json @@ -0,0 +1,16 @@ +{ + "Name": "TreeBankPT", + "URL": "https://hdl.handle.net/21.11129/0000-000B-D34B-3", + "Family": "Manually annotated corpora", + "Description": "This is a corpus of syntactic constituency trees. The sentences are translations from the Wall Street Journal.\nThe corpus is available from PORTULAN.", + "Language": ["por"], + "Licence": "CC BY", + "Size": ["3,406 sentences", "4,598 tokens"], + "Annotation": ["Syntactic parsing"], + "Infrastructure": "CLARIN", + "Group": ["Syntactic parsing"], + "Access": { + "Download": "https://hdl.handle.net/21.11129/0000-000B-D34B-3" + }, + "Publication": "" +} \ No newline at end of file