{"id":"W2328225175","doi":"10.1142/9789812704313_0009","title":"CREATING A NATURAL LANGUAGE INTERFACE FOR MULTI-AGENT SYSTEMS","year":2003,"lang":"en","type":"article","venue":"Active Media Technology","topic":"DNA and Biological Computing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Natural language user interface; Interface (matter); Natural (archaeology); Human–computer interaction; Interface description language; Natural language; User interface; Programming language; Natural language processing; Operating system","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":[0.002701053,0.0007613399,0.0006509378,0.0006590569,0.0008924591,0.002857925,0.002467679,0.002219224,0.01450547],"category_scores_gemma":[0.007837513,0.0008165463,0.001121465,0.000324546,0.001124545,0.004600905,0.004308827,0.002563881,0.003473367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005286794,"about_ca_system_score_gemma":0.0005565521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009599724,"about_ca_topic_score_gemma":0.001246485,"domain_scores_codex":[0.9986481,0.0005627558,0.0001395407,0.0001880118,0.0003771019,0.00008450919],"domain_scores_gemma":[0.9967705,0.002233449,0.0000963318,0.0003606424,0.0003523715,0.0001867996],"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":[0.001433157,0.001161127,0.00283397,0.00147369,0.0002417313,0.002725998,0.01280972,0.04416224,0.1423319,0.2502629,0.06226741,0.4782962],"study_design_scores_gemma":[0.0004103419,0.0002810735,0.000422939,0.000134179,0.0001578586,0.0008098631,0.000754943,0.5883433,0.07357848,0.08285043,0.2520977,0.0001589502],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008266826,0.00004434315,0.9731804,0.000279317,0.00007533412,0.0002089278,0.0001431466,0.01458733,0.003214351],"genre_scores_gemma":[0.1049921,0.0001029037,0.8806998,0.0003696947,0.00004701241,0.0007122518,0.0008015558,0.003500646,0.008774071],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01450547,"threshold_uncertainty_score":0.04852563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0192896177060654,"score_gpt":0.2947404985847568,"score_spread":0.2754508808786914,"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."}}