diff --git a/corpora/parallel-corpora/europarl-por-eng.json b/corpora/parallel-corpora/europarl-por-eng.json new file mode 100644 index 0000000..ec31b93 --- /dev/null +++ b/corpora/parallel-corpora/europarl-por-eng.json @@ -0,0 +1,16 @@ +{ + "Name": "EUROPARL Corpus Parallel Corpora: Portuguese-English", + "URL": "https://hdl.handle.net/21.11129/0000-000B-D33E-2 ", + "Family": "Parallel corpora", + "Description": "This is the Portuguese-English subset of the corpus.\nThe corpus contains transcriptions of sessions from 1996 to 2011.\nThe corpus is available from PORTULAN.", + "Language": ["Portuguese-English"], + "Licence": "CC BY-NC-SA", + "Size": ["49.2 million tokens (English)", "58.3 million tokens (Portuguese)"], + "Annotation": ["tokenised", "PoS-tagged", "lemmatised"], + "Infrastructure": "CLARIN", + "Group": ["Bilingual corpora"], + "Access": { + "Download": "https://hdl.handle.net/21.11129/0000-000B-D33E-2" + }, + "Publication": "http://www.propor2012.org/" +} \ No newline at end of file