{"url":"/dataset/trecqa","name":"TrecQA","full_name":"Text Retrieval Conference Question Answering","description_markdown":"**Text Retrieval Conference Question Answering** (**TrecQA**) is a dataset created from the TREC-8 (1999) to TREC-13 (2004) Question Answering tracks. There are two versions of TrecQA: raw and clean. Both versions have the same training set but their development and test sets differ. The commonly used clean version of the dataset excludes questions in development and test sets with no answers or only positive/negative answers. The clean version has 1,229/65/68 questions and 53,417/1,117/1,442 question-answer pairs for the train/dev/test split.\r\n\r\nSource: [A Gated Self-attention Memory Network for Answer Selection](https://arxiv.org/abs/1909.09696)","description_withheld":null,"homepage":"https://trec.nist.gov/data/qa.html","introduced_date":"2007-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA","first_author":null,"url":"https://www.aclweb.org/anthology/D07-1003/"},"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":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Answer Selection","url":"/task/answer-selection","datasets_with_task":"/datasets/task/answer-selection"}],"languages":[],"variants":["TrecQA","trec"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/CogComp/trec","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/trec","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":73,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-trecqa","task":"Question Answering","dataset_variant":"TrecQA","rows":13,"metrics":["MAP","MRR"],"first_row_in_archive_order":{"model":"TANDA DeBERTa-V3-Large + ALL","paper":"/paper/structural-self-supervised-objectives-for","metrics":{"MAP":"0.954","MRR":"0.984"},"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-trecqa-1","task":"Answer Selection","dataset_variant":"TrecQA","rows":1,"metrics":["MAP","MRR"],"first_row_in_archive_order":{"model":"RLAS-BIABC","paper":"/paper/rlas-biabc-a-reinforcement-learning-based","metrics":{"MAP":"0.913","MRR":"0.998"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-classification-on-trec-1","task":"Text Classification","dataset_variant":"trec","rows":0,"metrics":["Accuracy","F1 Macro","F1 Micro","F1 Weighted","Precision Macro","Precision Micro","Precision Weighted","Recall Macro","Recall Micro","Recall Weighted","loss"],"first_row_in_archive_order":null,"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/context-aware-transformer-pre-training-for","title":"Context-Aware Transformer Pre-Training for Answer Sentence Selection","date":"2023-05-24","rows_on_this_dataset":1,"code_links":0,"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":2,"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/towards-scalable-and-reliable-capsule","title":"Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications","date":"2019-06-06","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"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/anmm-ranking-short-answer-texts-with","title":"aNMM: Ranking Short Answer Texts with Attention-Based Neural Matching Model","date":"2018-01-05","rows_on_this_dataset":1,"code_links":1,"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/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/deep-learning-for-answer-sentence-selection","title":"Deep Learning for Answer Sentence Selection","date":"2014-12-04","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"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."}