{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002098889,0.0003579705,0.0004516626,0.0002867574,0.0003716555,0.001426005,0.003768739,0.0002326774,0.00004488849],"category_scores_gemma":[0.002656888,0.0003304993,0.0001232605,0.00007508342,0.00002865527,0.0004386079,0.005475588,0.0007814221,0.0001832702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001496928,"about_ca_system_score_gemma":0.0005998029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000658285,"about_ca_topic_score_gemma":0.00007290145,"domain_scores_codex":[0.9968956,0.0003438849,0.0004446042,0.001175384,0.000649325,0.0004911749],"domain_scores_gemma":[0.9960775,0.0002651869,0.0002581183,0.002947156,0.000168252,0.0002838289],"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":[0.00001071046,0.0000940908,0.001742112,0.000271903,0.00005626497,0.0001232024,0.01077201,0.1225695,0.0008581947,0.004058301,0.0002238089,0.8592199],"study_design_scores_gemma":[0.0001330352,0.00009968615,0.007770072,0.0002799677,0.0000150378,0.00001467768,0.00002504821,0.9787995,0.000744143,0.01113692,0.0004971857,0.0004847709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2784916,0.00005970152,0.7088608,0.001871261,0.001271698,0.0004614584,0.000002603524,0.001222487,0.007758445],"genre_scores_gemma":[0.7031056,0.000007532992,0.2936937,0.0002047582,0.0002567731,0.00006883663,0.000004006819,0.0000242741,0.00263452],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8587351,"threshold_uncertainty_score":0.9999147,"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."}}