{"id":"W2121479142","doi":"","title":"Collocation Extraction for Machine Translation","year":2003,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Collocation (remote sensing); Computer science; Natural language processing; Translation (biology); Artificial intelligence; Machine translation; Embedding; Information extraction; Extraction (chemistry); Machine translation software usability; Rule-based machine translation; Example-based machine translation; Machine learning","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":[0.0001914518,0.00004441385,0.00003853669,0.00004792329,0.00006119003,0.00005906078,0.0001245938,0.00003502399,0.000009125883],"category_scores_gemma":[0.00004626287,0.00003795754,0.00002021764,0.0001587823,0.00000454704,0.0004699562,0.000003620804,0.0000342422,0.000003007424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000020792,"about_ca_system_score_gemma":0.0000208563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007730171,"about_ca_topic_score_gemma":0.000009884419,"domain_scores_codex":[0.9996249,0.00001730069,0.00008175981,0.0001300252,0.00007239062,0.00007361366],"domain_scores_gemma":[0.9997178,0.00004989405,0.00003223731,0.0001265973,0.00005693269,0.00001653918],"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":[0.000003698977,0.00002610695,0.00002645437,0.0000141498,0.000002381769,2.848814e-7,0.000111472,0.000006423209,0.0219337,0.6053996,0.0004986265,0.3719771],"study_design_scores_gemma":[0.0003826231,0.00008378907,0.00004084591,0.00001056324,0.000005944813,0.00002267585,0.000009088332,0.1533208,0.5683419,0.2508494,0.02672882,0.0002036253],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007864376,0.0008496587,0.9957042,0.0005247697,0.00009280376,0.0001888071,3.87866e-7,0.0004039948,0.002156764],"genre_scores_gemma":[0.3648688,0.000002427164,0.6347458,0.00009565105,0.000006993751,0.00002059303,0.000002369165,0.000002340106,0.000254951],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5464082,"threshold_uncertainty_score":0.1547863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02199688784710613,"score_gpt":0.3105580019753942,"score_spread":0.2885611141282881,"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."}}