{"url":"/dataset/amharic-english-parallel-corpus-for-machine","name":"Amharic - English Parallel Corpus for Machine Translation","full_name":null,"description_markdown":"**Amharic - English Parallel Corpus for Machine Translation** contains 33,955 sentence pairs extracted text from such news platforms as Ethiopian Press Agency1, Fana Broadcasting Corporate2, and Walta Information Center3. As the data we used is from different sources, it includes various domains such as religious (Bible and Quran), politics, economics, sports, news, among others.\r\n\r\nSource: [The Effect of Normalization for Bi-directional Amharic-English Neural Machine Translation](https://arxiv.org/pdf/2210.15224v1.pdf)","description_withheld":null,"homepage":"","introduced_date":"2022-10-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-effect-of-normalization-for-bi","title":"The Effect of Normalization for Bi-directional Amharic-English Neural Machine Translation","first_author":"Tadesse Destaw Belay","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Amharic","url":"/datasets/language/amharic"}],"variants":["Amharic - English Parallel Corpus for Machine Translation"],"data_loaders":[],"num_papers_in_archive":2,"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."}