{"id":"W4390047559","doi":"10.1016/j.compind.2023.104063","title":"Neural semantic tagging for natural language-based search in building information models: Implications for practice","year":2023,"lang":"en","type":"article","venue":"Computers in Industry","topic":"BIM and Construction Integration","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Semantic search; Natural language; Information extraction; Artificial intelligence; Deep learning; Schema (genetic algorithms); Information retrieval; Data science; Natural language processing; Semantic Web","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002038331,0.00008202607,0.00008459987,0.0003612054,0.00005351813,0.00006768564,0.0001040724,0.0001460215,7.687648e-7],"category_scores_gemma":[0.00006721522,0.00009304441,0.00003153185,0.0004759498,0.00001348832,0.0006900357,0.00001511142,0.0003715809,0.000001610706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001172219,"about_ca_system_score_gemma":0.00003326407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002243334,"about_ca_topic_score_gemma":0.000009484307,"domain_scores_codex":[0.9994094,0.00001561483,0.0002193555,0.00009350738,0.00006012113,0.0002020114],"domain_scores_gemma":[0.9994748,0.0003063612,0.0000291283,0.0001042723,0.00006080153,0.0000246305],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001136617,0.00000494893,0.0003511219,0.00008827224,0.00000590488,4.468973e-7,0.0005431939,0.8939215,0.000392424,0.00422179,0.0008676854,0.09959134],"study_design_scores_gemma":[0.0004812256,0.00000894938,0.001014251,0.00006678199,0.00000369535,0.000005398892,0.0008534904,0.996257,0.0003210194,0.0005053735,0.0003862854,0.00009654273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4270934,0.00006638997,0.5680764,0.002552488,0.00102366,0.0006353894,0.00002571611,0.0003636218,0.0001629904],"genre_scores_gemma":[0.9821337,0.000002506368,0.01727071,0.0002188685,0.00008348103,0.0001824829,0.00009117993,0.00001204367,0.00000506813],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5550403,"threshold_uncertainty_score":0.3794241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02995210559364643,"score_gpt":0.3015647232939501,"score_spread":0.2716126177003036,"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."}}