{"url":"/dataset/insuranceqa","name":"InsuranceQA","full_name":null,"description_markdown":"**InsuranceQA** is a question answering dataset for the insurance domain, the data stemming from the website Insurance Library. There are 12,889 questions and 21,325 answers in the training set. There are 2,000 questions and 3,354 answers in the validation set. There are 2,000 questions and 3,308 answers in the test set.\r\n\r\nSource: [APPLYING DEEP LEARNING TO ANSWER SELECTION: A STUDY AND AN OPEN TASK](https://arxiv.org/pdf/1508.01585v2.pdf)","description_withheld":null,"homepage":"https://github.com/shuzi/insuranceQA","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/applying-deep-learning-to-answer-selection-a","title":"Applying Deep Learning to Answer Selection: A Study and An Open Task","first_author":"Minwei Feng","url":null},"license":{"name":"Unknown","url":null},"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":"Answer Selection","url":"/task/answer-selection","datasets_with_task":"/datasets/task/answer-selection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["InsuranceQA"],"data_loaders":[{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#insuranceqa","frameworks":["pytorch"]},{"repo":"https://github.com/shuzi/insuranceQA","url":"https://github.com/shuzi/insuranceQA","frameworks":[]}],"num_papers_in_archive":38,"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."}