{"id":"W2573346038","doi":"","title":"Predicting sentential semantic compatibility for aggregation in text-to-text generation","year":2016,"lang":"en","type":"article","venue":"International Conference on Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Sentence; Natural language processing; Artificial intelligence; Task (project management); Cluster analysis; Process (computing); Context (archaeology); Information retrieval","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":[0.005651951,0.001122228,0.0007154646,0.003934626,0.001130775,0.001980493,0.0009407126,0.001396344,0.001993907],"category_scores_gemma":[0.0345922,0.0003714665,0.0009722483,0.002372116,0.0005118169,0.003942818,0.001404012,0.00136352,0.001274905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000913418,"about_ca_system_score_gemma":0.001288601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003557357,"about_ca_topic_score_gemma":0.006092007,"domain_scores_codex":[0.9963157,0.001677354,0.0003383271,0.0008557483,0.0005903229,0.0002225627],"domain_scores_gemma":[0.9759448,0.01785277,0.001366986,0.001604183,0.002717842,0.0005133476],"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":[0.002287034,0.001042489,0.07798526,0.001145489,0.0003942559,0.000852232,0.002968399,0.06360371,0.05728237,0.01007382,0.02782758,0.7545374],"study_design_scores_gemma":[0.0001022418,0.0003683032,0.03686602,0.00006849034,0.0001934946,0.0003721606,0.0008095256,0.8931515,0.04463444,0.01722133,0.006120567,0.00009199715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6377878,0.001482883,0.3388717,0.0009890356,0.0002897285,0.0007476666,0.003938065,0.008942451,0.006950719],"genre_scores_gemma":[0.8106865,0.0001811969,0.1818631,0.00007538965,0.00009557742,0.0002179534,0.005738619,0.0003389973,0.0008026836],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005651951,"threshold_uncertainty_score":0.02989072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07688502906661919,"score_gpt":0.3287613563504564,"score_spread":0.2518763272838372,"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."}}