{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":12,"of":12,"counts":{"papers_with_a_benchmark_row":12,"with_a_code_link":7,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":12,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/structural-self-supervised-objectives-for","slug":"structural-self-supervised-objectives-for","title":"Structural Self-Supervised Objectives for Transformers","date":"2023-09-15","arxiv_id":"2309.08272","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/context-aware-transformer-pre-training-for","slug":"context-aware-transformer-pre-training-for","title":"Context-Aware Transformer Pre-Training for Answer Sentence Selection","date":"2023-05-24","arxiv_id":"2305.15358","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rlas-biabc-a-reinforcement-learning-based","slug":"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","arxiv_id":"2301.02807","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/pre-training-transformer-models-with-sentence","slug":"pre-training-transformer-models-with-sentence","title":"Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection","date":"2022-05-20","arxiv_id":"2205.10455","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/paragraph-based-transformer-pre-training-for","slug":"paragraph-based-transformer-pre-training-for","title":"Paragraph-based Transformer Pre-training for Multi-Sentence Inference","date":"2022-05-02","arxiv_id":"2205.01228","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tanda-transfer-and-adapt-pre-trained","slug":"tanda-transfer-and-adapt-pre-trained","title":"TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection","date":"2019-11-11","arxiv_id":"1911.04118","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/towards-scalable-and-reliable-capsule","slug":"towards-scalable-and-reliable-capsule","title":"Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications","date":"2019-06-06","arxiv_id":"1906.02829","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/a-compare-aggregate-model-with-latent","slug":"a-compare-aggregate-model-with-latent","title":"A Compare-Aggregate Model with Latent Clustering for Answer Selection","date":"2019-05-30","arxiv_id":"1905.12897","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/anmm-ranking-short-answer-texts-with","slug":"anmm-ranking-short-answer-texts-with","title":"aNMM: Ranking Short Answer Texts with Attention-Based Neural Matching Model","date":"2018-01-05","arxiv_id":"1801.01641","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hyperbolic-representation-learning-for-fast","slug":"hyperbolic-representation-learning-for-fast","title":"Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering","date":"2017-07-25","arxiv_id":"1707.07847","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pairwise-word-interaction-modeling-with-deep","slug":"pairwise-word-interaction-modeling-with-deep","title":"Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement","date":"2016-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-learning-for-answer-sentence-selection","slug":"deep-learning-for-answer-sentence-selection","title":"Deep Learning for Answer Sentence Selection","date":"2014-12-04","arxiv_id":"1412.1632","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/structural-self-supervised-objectives-for","slug":"structural-self-supervised-objectives-for","title":"Structural Self-Supervised Objectives for Transformers","date":"2023-09-15","arxiv_id":"2309.08272","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/context-aware-transformer-pre-training-for","slug":"context-aware-transformer-pre-training-for","title":"Context-Aware Transformer Pre-Training for Answer Sentence Selection","date":"2023-05-24","arxiv_id":"2305.15358","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rlas-biabc-a-reinforcement-learning-based","slug":"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","arxiv_id":"2301.02807","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/pre-training-transformer-models-with-sentence","slug":"pre-training-transformer-models-with-sentence","title":"Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection","date":"2022-05-20","arxiv_id":"2205.10455","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/paragraph-based-transformer-pre-training-for","slug":"paragraph-based-transformer-pre-training-for","title":"Paragraph-based Transformer Pre-training for Multi-Sentence Inference","date":"2022-05-02","arxiv_id":"2205.01228","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tanda-transfer-and-adapt-pre-trained","slug":"tanda-transfer-and-adapt-pre-trained","title":"TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection","date":"2019-11-11","arxiv_id":"1911.04118","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/towards-scalable-and-reliable-capsule","slug":"towards-scalable-and-reliable-capsule","title":"Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications","date":"2019-06-06","arxiv_id":"1906.02829","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/a-compare-aggregate-model-with-latent","slug":"a-compare-aggregate-model-with-latent","title":"A Compare-Aggregate Model with Latent Clustering for Answer Selection","date":"2019-05-30","arxiv_id":"1905.12897","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/anmm-ranking-short-answer-texts-with","slug":"anmm-ranking-short-answer-texts-with","title":"aNMM: Ranking Short Answer Texts with Attention-Based Neural Matching Model","date":"2018-01-05","arxiv_id":"1801.01641","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hyperbolic-representation-learning-for-fast","slug":"hyperbolic-representation-learning-for-fast","title":"Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering","date":"2017-07-25","arxiv_id":"1707.07847","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pairwise-word-interaction-modeling-with-deep","slug":"pairwise-word-interaction-modeling-with-deep","title":"Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement","date":"2016-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-learning-for-answer-sentence-selection","slug":"deep-learning-for-answer-sentence-selection","title":"Deep Learning for Answer Sentence Selection","date":"2014-12-04","arxiv_id":"1412.1632","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":0,"papers_with_a_run_with_no_instrument_failure":0,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"51624d0e2f1ba0ed4b57ebff1b9f4b6e62ac275169d775695b19c252229d8711","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}