{"id":"W2050154860","doi":"10.1111/1467-9671.00132","title":"Handling Grammatical Errors, Ambiguity and Impreciseness in GIS Natural Language Queries","year":2003,"lang":"en","type":"article","venue":"Transactions in GIS","topic":"Constraint Satisfaction and Optimization","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Executable; Ambiguity; Natural language; Natural language user interface; Query language; Parsing; RDF query language; Natural language processing; Artificial intelligence; Query expansion; Web query classification; Information retrieval; Web search query; Programming language; Search engine","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":[0.0002095395,0.00009665346,0.0001302247,0.0001861586,0.00008769998,0.00008157769,0.00009737906,0.0000628304,0.00008239614],"category_scores_gemma":[0.00004150471,0.00009900986,0.00003001233,0.0004473786,0.00007013873,0.0004187867,0.000005720147,0.0002089966,0.000003303285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005837799,"about_ca_system_score_gemma":0.00004650018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003472639,"about_ca_topic_score_gemma":0.004255828,"domain_scores_codex":[0.999191,0.00009180458,0.0002121659,0.0002192698,0.0001121974,0.0001735417],"domain_scores_gemma":[0.9996538,0.00008108422,0.00002683619,0.000171026,0.00002087561,0.00004642364],"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":[0.00004322185,0.0003396753,0.02462264,0.0001192915,0.00003816859,0.00009330666,0.02443952,0.01500837,0.003627769,0.0364504,0.00001917759,0.8951985],"study_design_scores_gemma":[0.004815742,0.000112162,0.2645193,0.0002441238,0.00003797918,0.000368419,0.005320909,0.7038426,0.01204348,0.005627759,0.001685079,0.001382474],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1874446,0.0001584611,0.8110434,0.0003775269,0.0002968492,0.0001207536,0.000002565974,0.00007405066,0.0004817805],"genre_scores_gemma":[0.9650002,0.00004838971,0.03475228,0.00004106015,0.000004815921,0.00001447418,0.000001608947,0.000004765139,0.0001324363],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.893816,"threshold_uncertainty_score":0.4037505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009359019516030484,"score_gpt":0.2494609606129916,"score_spread":0.2401019410969611,"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."}}