{"id":"W2123551014","doi":"10.3115/1220835.1220839","title":"Segment choice models","year":2006,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Perplexity; Computer science; Phrase; Distortion (music); Machine translation; Artificial intelligence; Decoding methods; Metric (unit); Probabilistic logic; Sentence; Translation (biology); Natural language processing; Sequence (biology); Language model; Speech recognition; Algorithm","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":[0.00006671729,0.00005908951,0.00004941695,0.00003960592,0.0000393907,0.0001085727,0.0005270606,0.00002769467,0.00001004096],"category_scores_gemma":[0.000004097291,0.00004513426,0.00001974705,0.0001520178,0.000009199435,0.000515963,0.0001490728,0.00005227874,0.00001709315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000242577,"about_ca_system_score_gemma":0.00001364764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003430171,"about_ca_topic_score_gemma":0.00002074066,"domain_scores_codex":[0.9994643,0.000008497507,0.00008147839,0.000171538,0.0001425297,0.0001316025],"domain_scores_gemma":[0.9996435,0.00001849224,0.00002259011,0.0002607518,0.0000342438,0.00002041349],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[2.519688e-7,0.00002250915,0.00004181822,0.00000377611,0.000001063949,0.000004787752,0.00001901551,0.00006306276,0.002418183,0.9590709,0.008279216,0.03007544],"study_design_scores_gemma":[0.00008051476,0.00001504356,0.00005582001,0.000008790382,0.000001099949,0.000008273283,0.000001058117,0.1630677,0.07641235,0.7578924,0.002308311,0.0001486171],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003966884,0.0006621271,0.9732611,0.0006572471,0.00004252175,0.00004805598,1.442474e-7,0.001068279,0.02386384],"genre_scores_gemma":[0.2855883,8.831616e-7,0.7118623,0.0003797506,0.00003628376,0.000005105134,5.416533e-7,0.000002699329,0.00212409],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2851916,"threshold_uncertainty_score":0.1840522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01276460161836465,"score_gpt":0.2531484317530582,"score_spread":0.2403838301346935,"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."}}