{"id":"W4396886508","doi":"10.1109/tkde.2024.3400824","title":"Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Visualization; Data visualization; Natural language; Information retrieval; Information visualization; Programming language; Database; World Wide Web; Natural language processing; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003462592,0.0001293568,0.0001276066,0.0001168375,0.0001036696,0.0001752863,0.0003941359,0.00003135126,0.000001904792],"category_scores_gemma":[0.00002288362,0.0001165779,0.00001015192,0.0002219632,0.00001726113,0.001736749,0.00005102776,0.0001067773,0.000003768537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001101872,"about_ca_system_score_gemma":0.00002580022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004332367,"about_ca_topic_score_gemma":0.0002764459,"domain_scores_codex":[0.9991218,0.00002020989,0.0001459665,0.0005090469,0.00006058941,0.0001423335],"domain_scores_gemma":[0.9988398,0.0002756728,0.00001300598,0.0007956169,0.00002471186,0.00005118045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008160728,0.0002248326,0.00004619582,0.005229327,0.0006571464,0.00008066191,0.009515133,0.006462435,0.02182146,0.0294847,0.007813312,0.9185832],"study_design_scores_gemma":[0.0001221323,0.00002336474,0.00002369549,0.000212411,0.00001354468,0.00001927936,0.00005498781,0.9632909,0.002123882,0.000003011438,0.03395004,0.0001627484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001725963,0.01337346,0.9818361,0.00002466967,0.00103592,0.0001359949,0.001643079,0.0002185885,0.000006158863],"genre_scores_gemma":[0.9652716,0.0003743615,0.03342944,0.00001228742,0.0001031138,0.00002073099,0.0006046438,0.00002468009,0.0001591711],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9635456,"threshold_uncertainty_score":0.4753908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04275557603702698,"score_gpt":0.3340007813895201,"score_spread":0.2912452053524931,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}