{"id":"W2039302098","doi":"10.3115/1654650.1654657","title":"Phrase-based SMT with shallow Tree-Phrases","year":2006,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Phrase; Natural language processing; Noun phrase; Artificial intelligence; Machine translation; Tree (set theory); Dependency (UML); Translation (biology); Dependency grammar; Specifier; Determiner phrase; Phrase structure rules; Simple (philosophy); Rule-based machine translation; Generative grammar; 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":[0.00009727821,0.0001485382,0.0001212561,0.0001083044,0.00007694113,0.0002087674,0.0007454932,0.00005089878,0.00003984122],"category_scores_gemma":[0.00001246019,0.00009875486,0.00003740327,0.0004099634,0.00004888112,0.0004030038,0.00007253223,0.00009893892,0.00001882548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003291816,"about_ca_system_score_gemma":0.00008003725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002417658,"about_ca_topic_score_gemma":0.0003871725,"domain_scores_codex":[0.9989855,0.00002274606,0.0001291433,0.0003383884,0.0002785056,0.000245759],"domain_scores_gemma":[0.9993261,0.00004781382,0.00005755027,0.000455282,0.000065338,0.0000479944],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007594899,0.0008083817,0.0152784,0.0001161068,0.00003375622,0.0006496836,0.0001661852,0.0002045064,0.03955633,0.6551796,0.03965972,0.2482715],"study_design_scores_gemma":[0.001532561,0.000496959,0.002089518,0.0001921875,0.00002223826,0.00005536705,0.00001840291,0.06393383,0.854134,0.06860416,0.00767546,0.001245381],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006724974,0.0005941,0.9794886,0.001767897,0.00003334228,0.0001131944,0.000001120366,0.002087862,0.009188924],"genre_scores_gemma":[0.5085239,2.508779e-7,0.4901021,0.0007019207,0.00002708334,0.00001035552,0.000003486248,0.000007199229,0.000623727],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8145776,"threshold_uncertainty_score":0.4027106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006299559038372088,"score_gpt":0.2203034535049582,"score_spread":0.2140038944665861,"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."}}