{"url":"/dataset/scb-mt-en-th-2020","name":"scb-mt-en-th-2020","full_name":null,"description_markdown":"scb-mt-en-th-2020 is an English-Thai machine translation dataset with over 1 million segment pairs, curated from various sources, namely news, Wikipedia articles, SMS messages, task-based dialogs, web-crawled data and government documents.\r\n\r\nSource: [scb-mt-en-th-2020: A Large English-Thai Parallel Corpus](/paper/scb-mt-en-th-2020-a-large-english-thai)\r\nImage Source: [Lowphansirikul et al](https://arxiv.org/pdf/2007.03541v1.pdf)","description_withheld":null,"homepage":"https://github.com/vistec-AI/dataset-releases/releases/tag/scb-mt-en-th-2020_v1.0","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/scb-mt-en-th-2020-a-large-english-thai","title":"scb-mt-en-th-2020: A Large English-Thai Parallel Corpus","first_author":"Lalita Lowphansirikul","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":[],"variants":["scb-mt-en-th-2020"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/airesearch/scb_mt_enth_2020","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/scb_mt_enth_2020","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/vistec-AI/dataset-releases","url":"https://github.com/vistec-AI/dataset-releases","frameworks":[]}],"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."}