{"id":"W2471177583","doi":"10.18653/v1/s16-1102","title":"CNRC at SemEval-2016 Task 1: Experiments in Crosslingual Semantic Textual Similarity","year":2016,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; SemEval; Semantic similarity; Natural language processing; Similarity (geometry); Artificial intelligence; Semantics (computer science); Machine translation; Task (project management); Information retrieval; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003947415,0.0002080569,0.0002052314,0.0001520857,0.0001169397,0.0001376349,0.001150633,0.0001314709,0.0001048031],"category_scores_gemma":[0.0001580453,0.000127279,0.00005804116,0.0002907657,0.0001008647,0.0007351011,0.001013326,0.0001257733,0.0001573748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002361541,"about_ca_system_score_gemma":0.00009484365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001408291,"about_ca_topic_score_gemma":0.0001020212,"domain_scores_codex":[0.9981597,0.00006985779,0.0003108405,0.0005947342,0.0003899886,0.0004748652],"domain_scores_gemma":[0.998949,0.0001244775,0.00008843701,0.0006530824,0.0000829342,0.0001020881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004572131,0.0002704814,0.006963989,0.00004001631,0.00002065725,0.000228804,0.001998083,7.094583e-7,0.8354911,0.03368023,0.008517957,0.1127422],"study_design_scores_gemma":[0.001003325,0.0001025969,0.00109591,0.0002199915,0.000003369116,0.00004396551,0.00002902687,0.0009632843,0.9753788,0.01799002,0.002603319,0.0005664128],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3447273,0.002576809,0.640308,0.002733506,0.0004856157,0.0005329152,0.00001060326,0.002437727,0.006187487],"genre_scores_gemma":[0.8819746,0.00001508141,0.1130348,0.0005606788,0.00005202239,0.0000164256,9.228053e-7,0.00001319665,0.004332218],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5372474,"threshold_uncertainty_score":0.5190287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02861404306301647,"score_gpt":0.3041952073667663,"score_spread":0.2755811643037498,"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."}}