{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003443438,0.001234278,0.001258008,0.001527459,0.0007176477,0.001909349,0.003597176,0.002002235,0.02566257],"category_scores_gemma":[0.01201911,0.0007374996,0.001810411,0.002403461,0.001262405,0.004754097,0.00199629,0.002539531,0.006459724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001744928,"about_ca_system_score_gemma":0.001246816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00565215,"about_ca_topic_score_gemma":0.006972077,"domain_scores_codex":[0.9977411,0.0009141765,0.0001151784,0.0006481285,0.0003839452,0.0001974777],"domain_scores_gemma":[0.9940279,0.004073055,0.0003530586,0.0008024874,0.0005095582,0.0002340893],"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":[0.001279815,0.0002366622,0.007970359,0.0003544934,0.0002895429,0.0004424666,0.0006305999,0.3338708,0.002553703,0.4528959,0.0267389,0.1727368],"study_design_scores_gemma":[0.00005367726,0.0000758669,0.0006916524,0.00002752086,0.00005949531,0.0001473866,0.00005288692,0.7812365,0.0008528476,0.2037423,0.01302467,0.00003515001],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03312961,0.001245614,0.9362863,0.001752266,0.0002847985,0.0003052514,0.004654159,0.001708569,0.02063346],"genre_scores_gemma":[0.7295245,0.001483166,0.1957326,0.0009476426,0.0004203872,0.0009727487,0.01060432,0.0009627133,0.05935194],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02566257,"threshold_uncertainty_score":0.08584988,"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."}}