{"id":"W157259314","doi":"","title":"Integrating Joint n-gram Features into a Discriminative Training Framework","year":2010,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Discriminative model; Transliteration; Computer science; Context (archaeology); Artificial intelligence; Joint (building); Generative grammar; n-gram; Transduction (biophysics); Feature (linguistics); String (physics); Context model; Natural language processing; Speech recognition; Machine learning; Pattern recognition (psychology); Language model; Engineering; Mathematics; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.0003724642,0.00017742,0.0001850822,0.0001265561,0.0002039944,0.0003599136,0.001014032,0.0001681525,0.00003708163],"category_scores_gemma":[0.001210781,0.0001340137,0.00007079243,0.000365332,0.0001093297,0.0004983582,0.0003418839,0.001297989,0.000008341625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003084763,"about_ca_system_score_gemma":0.00007351527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003196616,"about_ca_topic_score_gemma":0.00005842836,"domain_scores_codex":[0.9987993,0.0000477921,0.0001835135,0.0003930004,0.0002774675,0.000298976],"domain_scores_gemma":[0.9990292,0.0001632145,0.0001109905,0.0004876383,0.0001135891,0.00009543],"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":[0.000001229256,0.00001285296,0.000009310548,0.000009919083,0.000003975918,0.00001281555,0.01548939,6.693841e-8,0.1406719,0.4875332,0.0005038017,0.3557515],"study_design_scores_gemma":[0.00004845427,0.00005006523,0.0001004171,0.0001244781,0.000003623328,0.00003473011,0.0004372304,0.001903966,0.1016328,0.895062,0.0004017396,0.000200508],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01030842,0.0001789176,0.9758449,0.003125233,0.0005104562,0.0001493849,9.01451e-7,0.001064925,0.008816839],"genre_scores_gemma":[0.4796126,8.116932e-7,0.5198289,0.0003916998,0.00008767615,0.00001737385,8.359556e-7,0.000007766515,0.00005238414],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4693042,"threshold_uncertainty_score":0.5639187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01877825979771563,"score_gpt":0.2974458039104205,"score_spread":0.2786675441127049,"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."}}