{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009434328,0.00003598875,0.00004139615,0.0001156926,0.00002016492,0.00006097434,0.0001656978,0.00002440769,0.00001992703],"category_scores_gemma":[0.0001579823,0.0000335209,0.00001819644,0.0005319037,0.00000323282,0.0004527709,0.00001294711,0.00002660911,0.00002660434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000507677,"about_ca_system_score_gemma":0.00009983861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004391764,"about_ca_topic_score_gemma":0.000007607402,"domain_scores_codex":[0.9990641,0.00008356538,0.0001148241,0.000170595,0.0004998099,0.0000671298],"domain_scores_gemma":[0.9993916,0.00005417625,0.00003080225,0.0002750362,0.0002016263,0.00004683089],"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":[0.000002841254,0.00002361181,0.0009438784,0.000002206313,0.000003005784,5.664783e-7,0.0004921296,0.07116762,0.0003070705,0.01896663,0.0005637365,0.9075267],"study_design_scores_gemma":[0.0003677716,0.0000124681,0.0003319483,0.000001060289,0.000003694651,4.491316e-7,0.00001496061,0.9899393,0.002140414,0.006733577,0.0004118639,0.00004254017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004816497,0.00005602365,0.9786015,0.001174536,0.0002193513,0.0001374932,7.677531e-8,0.0001091912,0.01488536],"genre_scores_gemma":[0.6443576,3.618778e-7,0.3554412,0.0001256593,0.00002305975,0.000006995166,0.000003235977,0.000001501151,0.00004048177],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9187716,"threshold_uncertainty_score":0.1366943,"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."}}