{"url":"/dataset/word2word","name":"word2word","full_name":"word2word","description_markdown":"word2word contains easy-to-use word translations for 3,564 language pairs.\r\n\r\n- A large collection of freely & publicly available bilingual lexicons for 3,564 language pairs across 62 unique languages.\r\n- Easy-to-use Python interface for accessing top-k word translations and for building a new bilingual lexicon from a custom parallel corpus.\r\n- Constructed using a simple approach that yields bilingual lexicons with high coverage and competitive translation quality.\r\n\r\nSource: [word2word](https://pypi.org/project/word2word/)","description_withheld":null,"homepage":"https://pypi.org/project/word2word/","introduced_date":"2019-11-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/word2word-a-collection-of-bilingual-lexicons","title":"word2word: A Collection of Bilingual Lexicons for 3,564 Language Pairs","first_author":"Yo Joong Choe","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Data Augmentation","url":"/task/data-augmentation","datasets_with_task":"/datasets/task/data-augmentation"}],"languages":[],"variants":["word2word"],"data_loaders":[],"num_papers_in_archive":5,"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."}