{"id":"W2251142302","doi":"","title":"Natural Language Generation and Summarization at RALI","year":2013,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Automatic summarization; Computer science; Natural language generation; Natural language processing; Artificial intelligence; Natural (archaeology); Natural language; Linguistics; History","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":[0.003002654,0.0009209592,0.0009623954,0.001665414,0.00133888,0.003464215,0.001289882,0.001460783,0.01688624],"category_scores_gemma":[0.005474353,0.0006066325,0.0009507635,0.001325068,0.000967596,0.002989682,0.001848005,0.002461543,0.01575968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001539147,"about_ca_system_score_gemma":0.001069831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00227253,"about_ca_topic_score_gemma":0.002289484,"domain_scores_codex":[0.9971381,0.001112445,0.0001317403,0.0008641669,0.0005565574,0.0001970584],"domain_scores_gemma":[0.9982881,0.0007914324,0.00008243997,0.000314536,0.0003703731,0.0001531012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004348539,0.0003187128,0.0006928988,0.0004694226,0.0000986735,0.0005452025,0.00308859,0.01047146,0.04416889,0.08014414,0.1301998,0.7293673],"study_design_scores_gemma":[0.000220673,0.000455992,0.001618979,0.0002260453,0.00008783194,0.0009055822,0.0006391763,0.1742224,0.08725378,0.1093453,0.6248018,0.0002225263],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.018419,0.005896961,0.8883808,0.008201065,0.001247956,0.00037516,0.001659217,0.02705508,0.04876488],"genre_scores_gemma":[0.1854021,0.004184031,0.6665424,0.001313841,0.001681088,0.0005339139,0.008067843,0.00637991,0.125895],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01688624,"threshold_uncertainty_score":0.05649006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007345351739512658,"score_gpt":0.2356543313644533,"score_spread":0.2283089796249407,"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."}}