{"url":"/dataset/phrase-in-context","name":"Phrase-in-Context","full_name":"Phrase-in-Context","description_markdown":"Phrase in Context is a curated benchmark for phrase understanding and semantic search, consisting of three tasks of increasing difficulty: Phrase Similarity (PS), Phrase Retrieval (PR) and Phrase Sense Disambiguation (PSD). The datasets are annotated by 13 linguistic experts on Upwork and verified by two groups: ~1000 AMT crowdworkers and another set of 5 linguistic experts. PiC benchmark is distributed under CC-BY-NC 4.0.","description_withheld":null,"homepage":"https://phrase-in-context.github.io/","introduced_date":"2022-06-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/pic-a-phrase-in-context-dataset-for-phrase","title":"PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search","first_author":"Thang M. Pham","url":null},"license":{"name":"CC-BY-NC 4.0","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"Semantic Similarity","url":"/task/semantic-similarity","datasets_with_task":"/datasets/task/semantic-similarity"},{"name":"Natural Language Understanding","url":"/task/natural-language-understanding","datasets_with_task":"/datasets/task/natural-language-understanding"},{"name":"Semantic Retrieval","url":"/task/semantic-retrieval","datasets_with_task":"/datasets/task/semantic-retrieval"},{"name":"text similarity","url":"/task/text-similarity","datasets_with_task":"/datasets/task/text-similarity"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Phrase-in-Context"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/PiC/phrase_sense_disambiguation","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/PiC/phrase_retrieval","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/PiC/phrase_similarity","frameworks":["tf","pytorch","jax"]}],"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."}