{"url":"/dataset/sentence-compression","name":"Sentence Compression","full_name":null,"description_markdown":"Sentence Compression is a dataset where the syntactic trees of the compressions are subtrees of their uncompressed counterparts, and hence where supervised systems which require a structural alignment between the input and output can be successfully trained. \r\n\r\nSource: [Overcoming the Lack of Parallel Data in Sentence Compression](/paper/overcoming-the-lack-of-parallel-data-in)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/sentence-compression","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/overcoming-the-lack-of-parallel-data-in","title":"Overcoming the Lack of Parallel Data in Sentence Compression","first_author":"Katja Filippova","url":null},"license":{"name":"Custom","url":"https://github.com/google-research-datasets/sentence-compression"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Sentence Compression","url":"/task/sentence-compression","datasets_with_task":"/datasets/task/sentence-compression"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Google Dataset","Sentence Compression"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google-research-datasets/sent_comp","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/sent_comp","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/google-research-datasets/sentence-compression","url":"https://github.com/google-research-datasets/sentence-compression","frameworks":[]}],"num_papers_in_archive":63,"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."}