{"id":"W4390913029","doi":"10.21437/iscslp.2008-51","title":"Subword Latent Semantic Analysis for TextTiling-based Automatic Story Segmentation of Chinese Broadcast News","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Science North","funders":"","keywords":"Bigram; Computer science; Artificial intelligence; Speech recognition; Latent semantic analysis; Natural language processing; Robustness (evolution); Mandarin Chinese; Sentence; Treebank; Hidden Markov model; Segmentation; Character (mathematics); Text segmentation; Trigram; Annotation; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002201656,0.0001202512,0.0002734362,0.000398257,0.000109661,0.00002675146,0.0002646774,0.00003861848,0.0002243483],"category_scores_gemma":[0.00007549617,0.00009490133,0.0002726271,0.0008675983,0.00003355789,0.0001789949,0.0000241103,0.00003855165,0.00002843834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000330096,"about_ca_system_score_gemma":0.0000715112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005762202,"about_ca_topic_score_gemma":0.0000903992,"domain_scores_codex":[0.998973,0.00007161873,0.0002980188,0.0002524356,0.0002514136,0.0001535656],"domain_scores_gemma":[0.9990464,0.0002809198,0.0001505007,0.0003299212,0.0001242125,0.00006803226],"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":[0.00003975129,0.0008775605,0.3693389,0.0002425939,0.0009159941,0.00002393349,0.002141261,0.006148558,0.006567731,0.0002613057,0.001088618,0.6123538],"study_design_scores_gemma":[0.0004682284,0.00005677713,0.09351538,0.000008462947,0.00008131679,0.000004110637,0.00003813879,0.8998253,0.005739326,0.00009052791,0.00004038983,0.000132042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4484667,0.00001789127,0.5507416,0.0003006345,0.00005934426,0.0001646617,0.000002699885,0.00009516827,0.0001513582],"genre_scores_gemma":[0.8334804,0.000006019908,0.1659474,0.0002536288,0.00001273515,0.00002681706,0.000009134475,0.000005682265,0.0002581598],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8936768,"threshold_uncertainty_score":0.3869964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03312502395368702,"score_gpt":0.272342365913709,"score_spread":0.239217341960022,"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."}}