{"id":"W2124136969","doi":"10.3115/1075096.1075108","title":"A probability model to improve word alignment","year":2003,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Word (group theory); Natural language processing; Machine translation; Artificial intelligence; Translation (biology); Sentence; Context (archaeology); Statistical model; Probability model; Linguistics; Mathematics","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":[0.0003152083,0.00009825145,0.00008895752,0.00004301286,0.00004574262,0.0001087854,0.0005866229,0.00004005482,0.00001135587],"category_scores_gemma":[0.0001040417,0.00007461262,0.00003061744,0.0002456122,0.00001221083,0.0002606628,0.0001918397,0.00007450357,0.00002384219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008278002,"about_ca_system_score_gemma":0.00006931066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001224207,"about_ca_topic_score_gemma":0.000005453035,"domain_scores_codex":[0.9990405,0.00002702395,0.0001324374,0.0003806072,0.0001952465,0.0002241945],"domain_scores_gemma":[0.9992061,0.00001570299,0.00002576775,0.0005889463,0.00006301158,0.0001004842],"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":[0.000002242592,0.00006789884,0.00002639979,0.0000135522,0.000003191358,0.000002695575,0.0003605572,0.0001020231,0.01417688,0.9280538,0.00176943,0.05542132],"study_design_scores_gemma":[0.00007477726,0.00004645037,0.000004878372,0.000008211961,0.000001351742,0.000003660218,0.000004079568,0.03891777,0.2645694,0.6953186,0.0008674441,0.0001833045],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002772701,0.00008969577,0.989486,0.000950076,0.00005977584,0.0002974548,4.180247e-7,0.0006565923,0.005687261],"genre_scores_gemma":[0.3058607,3.338724e-7,0.692116,0.001016232,0.000004491701,0.0000415694,8.441045e-8,0.000003408645,0.0009571922],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.303088,"threshold_uncertainty_score":0.3042614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02319660031581302,"score_gpt":0.2710961346077686,"score_spread":0.2478995342919556,"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."}}