{"url":"/dataset/bilingual-corpus-of-arabic-english-parallel","name":"Bilingual Corpus of Arabic-English Parallel Tweets","full_name":null,"description_markdown":"A bilingual corpus of English-Arabic parallel tweets and a list of Twitter accounts who post English-Arabic tweets regularly.\r\n\r\nSource: [Constructing a Bilingual Corpus of Parallel Tweets](/paper/constructing-a-bilingual-corpus-of-parallel)","description_withheld":null,"homepage":"https://alt.qcri.org/resources/bilingual_corpus_of_parallel_tweets","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/constructing-a-bilingual-corpus-of-parallel","title":"Constructing a Bilingual Corpus of Parallel Tweets","first_author":"Hamdy Mubarak","url":null},"license":null,"modalities":[],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"}],"languages":[],"variants":["Bilingual Corpus of Arabic-English Parallel Tweets"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/alt-qsri/tweets_ar_en_parallel","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/tweets_ar_en_parallel","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/tweets_hate_speech_detection","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}