{"id":"W4293637667","doi":"10.48550/arxiv.1601.07124","title":"LIA-RAG: a system based on graphs and divergence of probabilities\\n applied to Speech-To-Text Summarization","year":2016,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Automatic summarization; Computer science; Task (project management); Divergence (linguistics); Natural language processing; Speech recognition; Artificial intelligence; Noise (video); Linguistics; Engineering","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":[0.001751511,0.001546981,0.001104652,0.003711235,0.0008042364,0.002128836,0.001921103,0.001502464,0.00665737],"category_scores_gemma":[0.007020559,0.0005601339,0.0009461214,0.001366346,0.0007201346,0.003681432,0.001973675,0.001592043,0.006557434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008124285,"about_ca_system_score_gemma":0.0008589788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003291423,"about_ca_topic_score_gemma":0.003782957,"domain_scores_codex":[0.998328,0.000582445,0.0001235779,0.0006225278,0.0002739659,0.00006951873],"domain_scores_gemma":[0.9972575,0.001351415,0.0002322331,0.0005422425,0.0004851758,0.000131514],"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":[0.0009569954,0.0001805093,0.001507626,0.001103858,0.0003073019,0.0004305013,0.0007666944,0.02017578,0.05681767,0.01446892,0.04935439,0.8539298],"study_design_scores_gemma":[0.0002550832,0.0004865162,0.002335198,0.0001136446,0.0002402023,0.0004566619,0.0003303392,0.776211,0.07364389,0.03867195,0.1070546,0.0002008704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007748365,0.0004250948,0.8233197,0.0002211462,0.000170217,0.0001949791,0.001761364,0.1644782,0.001680994],"genre_scores_gemma":[0.1085633,0.0002558061,0.8742415,0.0002737723,0.0002117983,0.0003741156,0.006626427,0.0051201,0.004333113],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00665737,"threshold_uncertainty_score":0.0222711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03069901152851088,"score_gpt":0.1834693841001352,"score_spread":0.1527703725716244,"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."}}