{"url":"/dataset/webquestionssp","name":"WebQuestionsSP","full_name":"WebQuestions Semantic Parses Dataset","description_markdown":"The WebQuestionsSP dataset is released as part of our ACL-2016 paper “The Value of Semantic Parse Labeling for Knowledge Base Question Answering” [Yih, Richardson, Meek, Chang & Suh, 2016], in which we evaluated the value of gathering semantic parses, vs. answers, for a set of questions that originally comes from WebQuestions [Berant et al., 2013]. The WebQuestionsSP dataset contains full semantic parses in SPARQL queries for 4,737 questions, and “partial” annotations for the remaining 1,073 questions for which a valid parse could not be formulated or where the question itself is bad or needs a descriptive answer. This release also includes an evaluation script and the output of the STAGG semantic parsing system when trained using the full semantic parses. More detail can be found in the document and labeling instructions included in this release, as well as the paper.\r\n\r\nSource: [WebQuestions Semantic Parses Dataset](https://www.microsoft.com/en-us/download/details.aspx?id=52763)","description_withheld":null,"homepage":"https://www.microsoft.com/en-us/download/details.aspx?id=52763","introduced_date":"2016-08-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-value-of-semantic-parse-labeling-for","title":"The Value of Semantic Parse Labeling for Knowledge Base Question Answering","first_author":"Wen-tau Yih","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":"Semantic Parsing","url":"/task/semantic-parsing","datasets_with_task":"/datasets/task/semantic-parsing"},{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"},{"name":"Knowledge Base Question Answering","url":"/task/knowledge-base-question-answering","datasets_with_task":"/datasets/task/knowledge-base-question-answering"}],"languages":[],"variants":["WebQSP-WD","WebQuestionsSP"],"data_loaders":[],"num_papers_in_archive":61,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/knowledge-base-question-answering-on-1","task":"Knowledge Base Question Answering","dataset_variant":"WebQuestionsSP","rows":8,"metrics":["Hits@1","F1","Accuracy"],"first_row_in_archive_order":{"model":"ChatKBQA","paper":"/paper/chatkbqa-a-generate-then-retrieve-framework","metrics":{"Accuracy":"77.8","F1":"83.5","Hits@1":"86.4"},"code_links":[{"title":"lhrlab/chatkbqa","url":"https://github.com/lhrlab/chatkbqa"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-parsing-on-webquestionssp","task":"Semantic Parsing","dataset_variant":"WebQuestionsSP","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ReaRev","paper":"/paper/rearev-adaptive-reasoning-for-question","metrics":{"Accuracy":"76.4"},"code_links":[{"title":"cmavro/rearev_kgqa","url":"https://github.com/cmavro/rearev_kgqa"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-webquestionssp","task":"Question Answering","dataset_variant":"WebQuestionsSP","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ChatGPT","paper":"/paper/evaluation-of-chatgpt-as-a-question-answering","metrics":{"Accuracy":"83.7"},"code_links":[{"title":"tan92hl/complex-question-answering-evaluation-of-gpt-family","url":"https://github.com/tan92hl/complex-question-answering-evaluation-of-gpt-family"},{"title":"tan92hl/complex-question-answering-evaluation-of-chatgpt","url":"https://github.com/tan92hl/complex-question-answering-evaluation-of-chatgpt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/sparkle-enhancing-sparql-generation-with","title":"SPARKLE: Enhancing SPARQL Generation with Direct KG Integration in Decoding","date":"2024-06-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/understand-what-llm-needs-dual-preference","title":"Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation","date":"2024-06-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/chatkbqa-a-generate-then-retrieve-framework","title":"ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models","date":"2023-10-13","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":8,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bridging-the-kb-text-gap-leveraging","title":"Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA","date":"2023-08-28","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":10,"samples_unverified":0,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/evaluation-of-chatgpt-as-a-question-answering","title":"Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family","date":"2023-03-14","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/rearev-adaptive-reasoning-for-question","title":"ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs","date":"2022-10-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/retrack-a-flexible-and-efficient-framework","title":"ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering","date":"2021-08-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/case-based-reasoning-for-natural-language","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","date":"2021-04-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-multi-hop-knowledge-base-question","title":"Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals","date":"2021-01-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unified-open-domain-question-answering-with","title":"UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering","date":"2020-12-29","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","rows_on_this_dataset":1,"code_links":57,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":31,"samples_ran":2,"samples_unverified":29,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-value-of-semantic-parse-labeling-for","title":"The Value of Semantic Parse Labeling for Knowledge Base Question Answering","date":"2016-08-01","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":4,"samples_harvested":60,"samples_ran":21,"samples_unverified":39,"pointer_only_for_licence":13,"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."}