{"url":"/dataset/wikiqa","name":"WikiQA","full_name":"Wikipedia open-domain Question Answering","description_markdown":"The **WikiQA** corpus is a publicly available set of question and sentence pairs, collected and annotated for research on open-domain question answering. In order to reflect the true information need of general users, Bing query logs were used as the question source. Each question is linked to a Wikipedia page that potentially has the answer. Because the summary section of a Wikipedia page provides the basic and usually most important information about the topic, sentences in this section were used as the candidate answers. The corpus includes 3,047 questions and 29,258 sentences, where 1,473 sentences were labeled as answer sentences to their corresponding questions.\r\n\r\nSource: [http://aka.ms/WikiQA](http://aka.ms/WikiQA)\r\nImage Source: [Yang et al](https://www.aclweb.org/anthology/D15-1237)","description_withheld":null,"homepage":"http://aka.ms/WikiQA","introduced_date":"2015-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/wikiqa-a-challenge-dataset-for-open-domain","title":"WikiQA: A Challenge Dataset for Open-Domain Question Answering","first_author":"Yi Yang","url":null},"license":{"name":"Custom","url":"https://www.microsoft.com/en-us/download/details.aspx?id=52419"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Answer Selection","url":"/task/answer-selection","datasets_with_task":"/datasets/task/answer-selection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WikiQA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/microsoft/wiki_qa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wiki_qa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#wikiqa","frameworks":["pytorch"]}],"num_papers_in_archive":196,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-wikiqa","task":"Question Answering","dataset_variant":"WikiQA","rows":25,"metrics":["MAP","MRR"],"first_row_in_archive_order":{"model":"TANDA-DeBERTa-V3-Large + ALL","paper":"/paper/structural-self-supervised-objectives-for","metrics":{"MAP":"0.927","MRR":"0.939"},"code_links":[{"title":"lucadiliello/transformers-framework","url":"https://github.com/lucadiliello/transformers-framework"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/answer-selection-on-wikiqa-1","task":"Answer Selection","dataset_variant":"WikiQA","rows":1,"metrics":["MAP "],"first_row_in_archive_order":{"model":"RLAS-BIABC","paper":"/paper/rlas-biabc-a-reinforcement-learning-based","metrics":{"MAP ":"0.888"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/structural-self-supervised-objectives-for","title":"Structural Self-Supervised Objectives for Transformers","date":"2023-09-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rlas-biabc-a-reinforcement-learning-based","title":"RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm","date":"2023-01-07","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/pre-training-transformer-models-with-sentence","title":"Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection","date":"2022-05-20","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/paragraph-based-transformer-pre-training-for","title":"Paragraph-based Transformer Pre-training for Multi-Sentence Inference","date":"2022-05-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tanda-transfer-and-adapt-pre-trained","title":"TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection","date":"2019-11-11","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/simple-and-effective-text-matching-with-1","title":"Simple and Effective Text Matching with Richer Alignment Features","date":"2019-08-01","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-compare-aggregate-model-with-latent","title":"A Compare-Aggregate Model with Latent Clustering for Answer Selection","date":"2019-05-30","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/noise-contrastive-estimation-and-negative","title":"Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency","date":"2018-09-06","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/baseline-needs-more-love-on-simple-word","title":"Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms","date":"2018-05-24","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/hyperbolic-representation-learning-for-fast","title":"Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering","date":"2017-07-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/neural-semantic-encoders","title":"Neural Semantic Encoders","date":"2016-07-14","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/key-value-memory-networks-for-directly","title":"Key-Value Memory Networks for Directly Reading Documents","date":"2016-06-09","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/pairwise-word-interaction-modeling-with-deep","title":"Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement","date":"2016-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sentence-similarity-learning-by-lexical","title":"Sentence Similarity Learning by Lexical Decomposition and Composition","date":"2016-02-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/attentive-pooling-networks","title":"Attentive Pooling Networks","date":"2016-02-11","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/neural-variational-inference-for-text","title":"Neural Variational Inference for Text Processing","date":"2015-11-19","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/wikiqa-a-challenge-dataset-for-open-domain","title":"WikiQA: A Challenge Dataset for Open-Domain Question Answering","date":"2015-09-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-learning-for-answer-sentence-selection","title":"Deep Learning for Answer Sentence Selection","date":"2014-12-04","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/distributed-representations-of-sentences-and","title":"Distributed Representations of Sentences and Documents","date":"2014-05-16","rows_on_this_dataset":2,"code_links":27,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":9,"samples_ran":2,"samples_unverified":7,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":1,"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."}