{"id":"W2251693562","doi":"10.3115/v1/p15-2025","title":"Representation Based Translation Evaluation Metrics","year":2015,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Chen; Computer science; Natural language processing; Representation (politics); Computational linguistics; Volume (thermodynamics); Joint (building); Translation (biology); Artificial intelligence; Association (psychology); Machine translation; Linguistics; Programming language; Engineering; Political science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01250151,0.001722331,0.001899459,0.01047092,0.001253025,0.003888244,0.001652714,0.001921651,0.004341125],"category_scores_gemma":[0.04201653,0.0003496502,0.001462891,0.0102701,0.0008509256,0.004999124,0.002777574,0.001525873,0.002273682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00248226,"about_ca_system_score_gemma":0.002091862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003103383,"about_ca_topic_score_gemma":0.003336858,"domain_scores_codex":[0.9732208,0.01427366,0.002264434,0.00183272,0.007467509,0.0009408561],"domain_scores_gemma":[0.9796178,0.008426024,0.001045961,0.003215884,0.007121608,0.0005728193],"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":[0.001576044,0.0006343924,0.01219141,0.001650272,0.0008149924,0.0002227188,0.0004367764,0.04416883,0.01221304,0.02885448,0.06316378,0.8340734],"study_design_scores_gemma":[0.0004211792,0.00298583,0.02073698,0.0007225154,0.001174881,0.001352953,0.0008883007,0.8003595,0.04134152,0.076364,0.0533318,0.0003205473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3008063,0.04223562,0.573213,0.004013471,0.002695109,0.001459875,0.01415264,0.01054578,0.05087812],"genre_scores_gemma":[0.7477977,0.003289222,0.2071736,0.0003289744,0.0004536948,0.0008037224,0.03182495,0.001365375,0.006962813],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01250151,"threshold_uncertainty_score":0.06611508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3391495938485538,"score_gpt":0.388191459149994,"score_spread":0.04904186530144017,"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."}}