{"id":"W2741333084","doi":"10.18653/v1/p17-1103","title":"Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research; McGill University","funders":"","keywords":"Turing test; Computer science; Utterance; Artificial intelligence; Quality (philosophy); Machine learning; Word (group theory); Test (biology); Natural language processing; Linguistics","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":[0.0291074,0.00339866,0.001992421,0.003187574,0.001445083,0.006037198,0.004705087,0.005428398,0.007817908],"category_scores_gemma":[0.1673957,0.001047248,0.001436192,0.001309238,0.002154665,0.008713468,0.009239824,0.005807073,0.0146677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001376135,"about_ca_system_score_gemma":0.001757659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001550442,"about_ca_topic_score_gemma":0.001926853,"domain_scores_codex":[0.948053,0.0396705,0.002564649,0.005502307,0.003114544,0.001094951],"domain_scores_gemma":[0.873756,0.08910325,0.003345606,0.01552285,0.01414642,0.004125815],"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":[0.004000738,0.002125274,0.02982928,0.001794062,0.0009759769,0.0002824504,0.003074563,0.0264186,0.01417755,0.01128887,0.1089532,0.7970795],"study_design_scores_gemma":[0.0009275837,0.002257012,0.01399688,0.000556135,0.0003124893,0.0003992845,0.002738547,0.826465,0.02764186,0.09389965,0.030519,0.0002866508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2727725,0.004444486,0.6387936,0.00445531,0.002932832,0.002111137,0.006610002,0.03972713,0.02815297],"genre_scores_gemma":[0.7342633,0.0004567349,0.2383631,0.001538109,0.000560769,0.002293207,0.01407406,0.00174471,0.006705988],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0291074,"threshold_uncertainty_score":0.1539364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0891649191737554,"score_gpt":0.3512603510742284,"score_spread":0.262095431900473,"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."}}