{"id":"W1492071093","doi":"10.48550/arxiv.1401.0509","title":"Zero-Shot Learning for Semantic Utterance Classification","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Semantic space; Utterance; Discriminative model; Zero (linguistics); Classifier (UML); Natural language processing; Training set; Machine learning; 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"],"consensus_categories":[],"category_scores_codex":[0.0002206203,0.0002414243,0.0002596754,0.000174136,0.0001883066,0.0001801083,0.001527386,0.0001945991,0.00001448092],"category_scores_gemma":[0.00004170234,0.000291463,0.0001692993,0.0002215057,0.0000429285,0.0004182281,0.0008460074,0.0005064884,0.0001099624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001490617,"about_ca_system_score_gemma":0.0001052279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008403957,"about_ca_topic_score_gemma":0.000008896048,"domain_scores_codex":[0.9981558,0.00009233124,0.000205376,0.001133677,0.00007849179,0.0003343647],"domain_scores_gemma":[0.9982303,0.0001168434,0.0002744277,0.001081798,0.0001933195,0.0001032695],"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":[0.000009860473,0.00004489415,0.002979233,0.0002096551,0.00005470665,0.00001974377,0.0004157834,0.6449543,0.0004700306,0.345305,0.0003812842,0.005155609],"study_design_scores_gemma":[0.0002454843,0.00001735448,0.0009486873,0.00007920404,0.00002456433,0.00000145912,0.00002237187,0.9469495,0.00008357211,0.05003686,0.001294592,0.000296389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1977223,0.00002950972,0.7998136,0.0002141364,0.0005304945,0.0003901872,0.000001356833,0.0002416469,0.001056846],"genre_scores_gemma":[0.9839026,0.00004743586,0.0113314,0.00009431745,0.0001019094,0.000005890944,0.00001363734,0.00001806732,0.004484703],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7884821,"threshold_uncertainty_score":0.9999537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1472474354119156,"score_gpt":0.2109788159159037,"score_spread":0.0637313805039881,"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."}}