{"url":"/dataset/latamxix","name":"LatamXIX","full_name":"19th Century Latin American Spanish Newspaper Corpus with LLM OCR Correction","description_markdown":"A novel dataset of 19th-century Latin American press texts, which addresses the lack of specialized corpora for historical and linguistic analysis in this region.","description_withheld":null,"homepage":"https://huggingface.co/datasets/Flaglab/latam-xix","introduced_date":"2024-07-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/historical-ink-19th-century-latin-american","title":"Historical Ink: 19th Century Latin American Spanish Newspaper Corpus with LLM OCR Correction","first_author":"Laura Manrique-Gómez","url":null},"license":{"name":"MIT","url":null},"modalities":[],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Sentiment Analysis","url":"/task/sentiment-analysis","datasets_with_task":"/datasets/task/sentiment-analysis"},{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"},{"name":"Hate Speech Detection","url":"/task/hate-speech-detection","datasets_with_task":"/datasets/task/hate-speech-detection"},{"name":"Slot Filling","url":"/task/slot-filling","datasets_with_task":"/datasets/task/slot-filling"},{"name":"Text Retrieval","url":"/task/text-retrieval","datasets_with_task":"/datasets/task/text-retrieval"},{"name":"Named Entity Recognition","url":"/task/named-entity-recognition-1","datasets_with_task":"/datasets/task/named-entity-recognition-1"},{"name":"Semantic Similarity","url":"/task/semantic-similarity","datasets_with_task":"/datasets/task/semantic-similarity"},{"name":"Topic Classification","url":"/task/topic-classification","datasets_with_task":"/datasets/task/topic-classification"},{"name":"Masked Language Modeling","url":"/task/masked-language-modeling","datasets_with_task":"/datasets/task/masked-language-modeling"},{"name":"Sentiment Classification","url":"/task/sentiment-classification","datasets_with_task":"/datasets/task/sentiment-classification"}],"languages":[{"name":"Old Spanish","url":"/datasets/language/old-spanish"}],"variants":["LatamXIX"],"data_loaders":[],"num_papers_in_archive":2,"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."}