{"url":"/dataset/english-web-treebank","name":"English Web Treebank","full_name":"English Web Treebank","description_markdown":"**English Web Treebank** is a dataset containing 254,830 word-level tokens and 16,624 sentence-level tokens of webtext in 1174 files annotated for sentence- and word-level tokenization, part-of-speech, and syntactic structure. The data is roughly evenly divided across five genres: weblogs, newsgroups, email, reviews, and question-answers. The files were manually annotated following the sentence-level tokenization guidelines for web text and the word-level tokenization guidelines developed for English treebanks in the DARPA GALE project. Only text from the subject line and message body of posts, articles, messages and question-answers were collected and annotated.\r\n\r\nSource: [https://catalog.ldc.upenn.edu/LDC2012T13](https://catalog.ldc.upenn.edu/LDC2012T13)","description_withheld":null,"homepage":"https://catalog.ldc.upenn.edu/LDC2012T13","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":null,"title":"English web treebank","first_author":null,"url":"http://www.ldc.upenn.edu/Catalog/catalogEntry.jsp?catalogId=L%DC2012T13"},"license":{"name":"Custom","url":"https://catalog.ldc.upenn.edu/LDC2012T13"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Dependency Parsing","url":"/task/dependency-parsing","datasets_with_task":"/datasets/task/dependency-parsing"},{"name":"Coreference Resolution","url":"/task/coreference-resolution","datasets_with_task":"/datasets/task/coreference-resolution"},{"name":"Part-Of-Speech Tagging","url":"/task/part-of-speech-tagging","datasets_with_task":"/datasets/task/part-of-speech-tagging"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["English Web Treebank"],"data_loaders":[],"num_papers_in_archive":42,"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."}