{"id":"W1633230169","doi":"10.1609/aimag.v35i1.2502","title":"Natural Language Access to Enterprise Data","year":2014,"lang":"en","type":"article","venue":"AI Magazine","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Siemens (Canada)","funders":"","keywords":"Computer science; Syntax; Data control language; Semantics (computer science); Natural language; Set (abstract data type); Data access; Enterprise data management; Question answering; Interpretation (philosophy); Query language; Data manipulation language; Programming language; Information retrieval; Enterprise information system; Database; World Wide Web; Data science; Artificial intelligence; Web search query; Query by Example","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004304687,0.0004880755,0.000694237,0.003260238,0.001085464,0.003359823,0.001678983,0.001092792,0.007082683],"category_scores_gemma":[0.01864573,0.0004677748,0.0008317572,0.003200962,0.001058281,0.006975198,0.00398255,0.001331233,0.002404803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009779414,"about_ca_system_score_gemma":0.001422297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004911168,"about_ca_topic_score_gemma":0.005467359,"domain_scores_codex":[0.9954464,0.001911968,0.0004206337,0.0008571901,0.001153593,0.0002102355],"domain_scores_gemma":[0.9888912,0.00722156,0.0004495294,0.00214752,0.001072586,0.0002175059],"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":[0.0004317778,0.0003461415,0.006295201,0.001690098,0.0001932983,0.001742037,0.009607168,0.01217822,0.02598989,0.2351173,0.1465044,0.5599045],"study_design_scores_gemma":[0.00007103181,0.00007073404,0.002274801,0.0002377583,0.00006761814,0.0008615289,0.001812017,0.1152554,0.0134701,0.2840585,0.5817149,0.0001055044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03586297,0.002903619,0.876354,0.006995383,0.0001880165,0.0004301303,0.0127794,0.03278613,0.03170025],"genre_scores_gemma":[0.4190001,0.003325294,0.5102888,0.003780253,0.0005647548,0.0006297521,0.04604773,0.00273053,0.0136329],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007082683,"threshold_uncertainty_score":0.02369392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02627650944316974,"score_gpt":0.3160102430337011,"score_spread":0.2897337335905314,"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."}}