{"id":"W2742155240","doi":"10.18653/v1/w17-2512","title":"Overview of the Second BUCC Shared Task: Spotting Parallel Sentences in Comparable Corpora","year":2017,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Nautical Research Society","funders":"European Commission","keywords":"Sentence; Computer science; German; Task (project management); Natural language processing; Artificial intelligence; Parallel corpora; Gold standard (test); Spotting; Sample (material); Speech recognition; Linguistics; Statistics; Mathematics; Machine translation","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":[0.0004084991,0.0001072027,0.0002035665,0.00004573844,0.0002059123,0.0002803689,0.002811609,0.00004901543,0.00006610798],"category_scores_gemma":[0.00009238374,0.00006688513,0.00005647834,0.0001533144,0.0001038848,0.0007804108,0.0008108987,0.0001679274,0.000005541754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001938763,"about_ca_system_score_gemma":0.00005795987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004519843,"about_ca_topic_score_gemma":0.0006184983,"domain_scores_codex":[0.9990262,0.00004761536,0.000250071,0.0002547613,0.0002220629,0.0001993308],"domain_scores_gemma":[0.9985045,0.00005282851,0.0003853226,0.0009587167,0.00006905818,0.00002959589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003642204,0.0003798923,0.3000742,0.001234038,0.00006228672,0.0001306938,0.003792702,0.00005147492,0.02777993,0.5765153,0.0183231,0.07161996],"study_design_scores_gemma":[0.00182953,0.0001336633,0.2390532,0.002806685,0.00001697723,0.0001148382,0.000267618,0.1115231,0.1584796,0.4773737,0.007119977,0.001281116],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7026548,0.02719003,0.1881184,0.01632878,0.001704205,0.002169685,0.0000397065,0.001485802,0.06030863],"genre_scores_gemma":[0.7924618,0.00001156467,0.206111,0.0002688551,0.0000114131,0.000005804127,4.451857e-7,0.000003594997,0.001125475],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1306997,"threshold_uncertainty_score":0.5224715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05596415462690715,"score_gpt":0.3149779532429419,"score_spread":0.2590137986160347,"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."}}