{"id":"W2115848042","doi":"","title":"On Hierarchical Re-ordering and Permutation Parsing for Phrase-based Decoding","year":2012,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Parsing; Permutation (music); Decoding methods; Phrase; Rule-based machine translation; Artificial intelligence; Machine translation; Constraint (computer-aided design); Hierarchical database model; Theoretical computer science; Natural language processing; Algorithm; Data mining; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002934842,0.00007729869,0.00007637501,0.00008082982,0.000139744,0.0001022576,0.0001647508,0.00004376159,0.00000498572],"category_scores_gemma":[0.0001881315,0.00006941676,0.00002236852,0.00009866967,0.00002281624,0.0003404478,0.00004708492,0.0001021783,0.000001326565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003504318,"about_ca_system_score_gemma":0.00001893919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001255467,"about_ca_topic_score_gemma":6.821867e-7,"domain_scores_codex":[0.9993653,0.0000264258,0.00009214845,0.000171662,0.0001191663,0.0002252688],"domain_scores_gemma":[0.9995089,0.0002158368,0.00003937006,0.0001420176,0.00002640442,0.00006751075],"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":[0.00004273295,0.00007002142,0.000455556,0.0001147645,0.0000061531,0.000003714973,0.001897789,0.00002162185,0.08123787,0.2302157,0.0005356784,0.6853984],"study_design_scores_gemma":[0.0005755619,0.0001700459,0.0002696888,0.0002221004,0.00001021751,0.00001431526,0.00002908817,0.4102146,0.24755,0.3401469,0.0004374752,0.0003600382],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08844525,0.0002016126,0.9094537,0.001009493,0.00008836731,0.0001229194,7.97218e-7,0.0002683143,0.0004094731],"genre_scores_gemma":[0.5376285,5.435576e-7,0.4620466,0.0002694488,0.00003609071,0.000007690104,0.000001184873,0.000004593132,0.000005383897],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6850383,"threshold_uncertainty_score":0.2830733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02318303471784058,"score_gpt":0.2976715664874585,"score_spread":0.2744885317696179,"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."}}