{"id":"W2896826757","doi":"10.1007/s10579-018-9430-2","title":"VERTa: a linguistic approach to automatic machine translation evaluation","year":2018,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España; Alberta-Pacific Forest Industries","keywords":"Metric (unit); Computer science; Machine translation; Natural language processing; Variety (cybernetics); Artificial intelligence; Linguistics; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.002261811,0.0001442597,0.0001395922,0.0001988622,0.0001879458,0.0002371628,0.0003168899,0.00007584579,0.00003836861],"category_scores_gemma":[0.0005025927,0.0001216624,0.00002963949,0.0004712407,0.00003635996,0.000241373,0.00007652646,0.00009440009,0.00001873319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000780308,"about_ca_system_score_gemma":0.00004767184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001286176,"about_ca_topic_score_gemma":0.00004108728,"domain_scores_codex":[0.998081,0.0002486102,0.0002273355,0.0004103941,0.000834307,0.0001983261],"domain_scores_gemma":[0.9990516,0.00006839908,0.00009724451,0.0003688078,0.0003298882,0.00008405178],"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":[0.00000868506,0.00003256407,0.00003541557,0.0000407094,0.00001036577,7.146752e-7,0.03481027,0.00005243864,0.001945418,0.0007063916,0.00007614926,0.9622809],"study_design_scores_gemma":[0.0003631843,0.0001152395,0.0005619292,0.00005731983,0.00005770868,0.00001346892,0.0001561246,0.9929041,0.001299783,0.00395254,0.0003493329,0.0001693247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2743939,0.01596119,0.7005414,0.0005098279,0.0002063716,0.001469178,0.000003615607,0.0006882392,0.006226347],"genre_scores_gemma":[0.7312979,0.000003074021,0.2681991,0.0001879124,0.0001833747,0.00007200095,0.00002211005,0.000009359922,0.0000252416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9928516,"threshold_uncertainty_score":0.4961249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03038743013763573,"score_gpt":0.3296793279805589,"score_spread":0.2992918978429232,"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."}}