{"url":"/dataset/ntext","name":"NText","full_name":null,"description_markdown":"NText is an eight million words dataset extracted and preprocessed from nuclear research papers and thesis.\r\n\r\nSource: [NukeBERT: A Pre-trained language model for Low Resource Nuclear Domain](https://arxiv.org/pdf/2003.13821.pdf)","description_withheld":null,"homepage":"https://github.com/ayushjain1144/NukeBERT","introduced_date":"2020-03-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/nukebert-a-pre-trained-language-model-for-low","title":"NukeBERT: A Pre-trained language model for Low Resource Nuclear Domain","first_author":"Ayush Jain","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[],"variants":["NText"],"data_loaders":[{"repo":"https://github.com/ayushjain1144/NukeBERT","url":"https://github.com/ayushjain1144/NukeBERT","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."}