{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/text-to-sql-in-the-wild-a-naturally-occurring","title":"Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data","arxiv_id":"2106.05006","date":"2021-06-09","proceeding":"ACL (NLP4Prog) 2021 8","authors":["Moshe Hazoom","Vibhor Malik","Ben Bogin"],"abstract":"Most available semantic parsing datasets, comprising of pairs of natural utterances and logical forms, were collected solely for the purpose of training and evaluation of natural language understanding systems. As a result, they do not contain any of the richness and variety of natural-occurring utterances, where humans ask about data they need or are curious about. In this work, we release SEDE, a dataset with 12,023 pairs of utterances and SQL queries collected from real usage on the Stack Exchange website. We show that these pairs contain a variety of real-world challenges which were rarely reflected so far in any other semantic parsing dataset, propose an evaluation metric based on comparison of partial query clauses that is more suitable for real-world queries, and conduct experiments with strong baselines, showing a large gap between the performance on SEDE compared to other common datasets.","url_abs":"https://arxiv.org/abs/2106.05006v1","url_pdf":"https://arxiv.org/pdf/2106.05006v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"text-to-sql-in-the-wild-a-naturally-occurring","repo_url":"https://github.com/hirupert/sede","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"},{"task_slug":"text-to-sql","task_name":"Text to SQL"},{"task_slug":"text-to-sql","task_name":"Text-To-SQL"}],"methods":[],"datasets_introduced":[{"slug":"sede","name":"SEDE","full_name":"Stack Exchange Data Explorer"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-sql-on-sede","task":"Text-To-SQL","dataset":"SEDE","model":"T5-Large","rank_in_archive_order":1,"of":1,"metrics":{"PCM-F1 (dev)":"48.2","PCM-F1 (test)":"50.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.05006","atlas_url":"https://app.syntology.ai/?focus=2106.05006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05006"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hirupert/sede","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"4d680eba792d9d58","entry":"add_schema_description","repo":"hirupert/sede","repo_kind":"official","path":"src/preprocessing/preprocess.py","file_url":"https://github.com/hirupert/sede/blob/HEAD/src/preprocessing/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4d680eba792d9d58"}},{"code_sha256_prefix":"f523c4d648a7a510","entry":"clean_str","repo":"hirupert/sede","repo_kind":"official","path":"src/preprocessing/preprocess.py","file_url":"https://github.com/hirupert/sede/blob/HEAD/src/preprocessing/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f523c4d648a7a510"}},{"code_sha256_prefix":"34a9ad8ddd29afcd","entry":"preprocess","repo":"hirupert/sede","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/hirupert/sede/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"34a9ad8ddd29afcd"}},{"code_sha256_prefix":"8fe7ef05eb8ff56f","entry":"remove_sql_comm","repo":"hirupert/sede","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/hirupert/sede/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8fe7ef05eb8ff56f"}},{"code_sha256_prefix":"8ac5261604f67eef","entry":"split_sql_text","repo":"hirupert/sede","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/hirupert/sede/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ac5261604f67eef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}