{"url":"/dataset/aspec","name":"ASPEC","full_name":"Asian Scientific Paper Excerpt Corpus","description_markdown":"**ASPEC**, Asian Scientific Paper Excerpt Corpus, is constructed by the Japan Science and Technology Agency (JST) in collaboration with the National Institute of Information and Communications Technology (NICT). It consists of a Japanese-English paper abstract corpus of 3M parallel sentences (ASPEC-JE) and a Japanese-Chinese paper excerpt corpus of 680K parallel sentences (ASPEC-JC). This corpus is one of the achievements of the Japanese-Chinese machine translation project which was run in Japan from 2006 to 2010.\r\n\r\nSource: [ASPEC](http://lotus.kuee.kyoto-u.ac.jp/ASPEC/)\r\nImage Source: [https://www.aclweb.org/anthology/L16-1350.pdf](https://www.aclweb.org/anthology/L16-1350.pdf)","description_withheld":null,"homepage":"http://lotus.kuee.kyoto-u.ac.jp/ASPEC/","introduced_date":"2016-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/aspec-asian-scientific-paper-excerpt-corpus","title":"ASPEC: Asian Scientific Paper Excerpt Corpus","first_author":"Toshiaki Nakazawa","url":null},"license":{"name":"Custom (non-commercial)","url":"https://jipsti.jst.go.jp/aspec/terms_en.html"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Domain Adaptation","url":"/task/domain-adaptation","datasets_with_task":"/datasets/task/domain-adaptation"},{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Low-Resource Neural Machine Translation","url":"/task/low-resource-neural-machine-translation","datasets_with_task":"/datasets/task/low-resource-neural-machine-translation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Japanese","url":"/datasets/language/japanese"}],"variants":["ASPEC"],"data_loaders":[],"num_papers_in_archive":87,"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."}