{"id":"W2950582891","doi":"10.48550/arxiv.1703.07713","title":"Hierarchical RNN with Static Sentence-Level Attention for Text-Based Speaker Change Detection","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Dialog box; Recurrent neural network; Sentence; Feature (linguistics); Speech recognition; Task (project management); Artificial intelligence; Matching (statistics); Point (geometry); Artificial neural network; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008604053,0.0009762783,0.0005671962,0.0006109437,0.0002975015,0.0003751926,0.001065869,0.0007164518,0.001924702],"category_scores_gemma":[0.002284735,0.0002962179,0.0005505266,0.0004673354,0.0002795159,0.0009995411,0.0007185425,0.001084572,0.0009600422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007021275,"about_ca_system_score_gemma":0.0007771401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01050411,"about_ca_topic_score_gemma":0.01518407,"domain_scores_codex":[0.9995394,0.0001105931,0.0000266442,0.0001939619,0.00007226472,0.00005717548],"domain_scores_gemma":[0.9992753,0.0003545316,0.00007355877,0.00007094711,0.0001892703,0.00003637012],"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":[0.0005365667,0.0003545105,0.002711736,0.0002337346,0.0001549856,0.0003543138,0.0003085792,0.1978197,0.07819709,0.003875519,0.007773827,0.7076795],"study_design_scores_gemma":[0.00000677836,0.00004512608,0.0006057123,0.000006163261,0.00002820589,0.00002893911,0.0000141104,0.9919133,0.005374921,0.001443855,0.0005240819,0.000008687282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1126332,0.001471391,0.8755112,0.0004175081,0.0002518949,0.0001324677,0.0005023647,0.005509964,0.003569929],"genre_scores_gemma":[0.7965047,0.0003569897,0.1957422,0.0003292892,0.0001582227,0.0001515698,0.001110409,0.0002062501,0.005440487],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01050411,"threshold_uncertainty_score":0.02088588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1273654846581534,"score_gpt":0.2345413229821426,"score_spread":0.1071758383239892,"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."}}