{"id":"W3032097118","doi":"","title":"Multilingual Corpus Creation for Multilingual Semantic Similarity Task","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; Western University","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Task (project management); Semantic similarity; Similarity (geometry); Sentence; Focus (optics); Information retrieval","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":[0.000651133,0.0001094603,0.0001359102,0.00004005731,0.0001391548,0.0001348659,0.0001954575,0.00006697531,0.000008505257],"category_scores_gemma":[0.0005390021,0.0001025502,0.00004490805,0.0001083673,0.00002001928,0.0001694708,0.00008734562,0.00008081119,0.000004162205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002269638,"about_ca_system_score_gemma":0.00003501023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001020411,"about_ca_topic_score_gemma":0.00003752065,"domain_scores_codex":[0.9987983,0.00009159589,0.0002094174,0.0003913254,0.0003370738,0.0001722481],"domain_scores_gemma":[0.9993408,0.0001434954,0.00009551755,0.0002046462,0.0001243692,0.00009121212],"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":[0.00004351504,0.00003289411,0.00107606,0.0001073634,0.00002194221,0.00000533914,0.07613178,0.007543406,0.009864903,0.0002749216,0.00004565271,0.9048522],"study_design_scores_gemma":[0.0008059164,0.00007386634,0.001124929,0.00001664067,0.00003159022,0.000003204335,0.0008750768,0.9926744,0.003142496,0.0002429724,0.0008877255,0.0001211513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8038204,0.0008858159,0.1937295,0.0008247023,0.00008797162,0.0004271514,0.000005159732,0.0001047696,0.0001144575],"genre_scores_gemma":[0.980028,0.000009841014,0.0190921,0.0004650367,0.0003156062,0.00002424928,0.00002241176,0.000008750627,0.00003397029],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.985131,"threshold_uncertainty_score":0.4181875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04671167661381604,"score_gpt":0.3280433324245093,"score_spread":0.2813316558106933,"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."}}