{"id":"W2807293832","doi":"10.18653/v1/s18-1118","title":"SUNNYNLP at SemEval-2018 Task 10: A Support-Vector-Machine-Based Method for Detecting Semantic Difference using Taxonomy and Word Embedding Features","year":2018,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Chinese University of Hong Kong; University of Toronto; Universiteit Utrecht","keywords":"SemEval; Computer science; Support vector machine; Discriminative model; Taxonomy (biology); Word embedding; Artificial intelligence; Natural language processing; Task (project management); Embedding; Word (group theory); Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004337295,0.002979521,0.001988819,0.00440951,0.001267171,0.002572732,0.00436822,0.003107339,0.01424229],"category_scores_gemma":[0.01389522,0.0008219202,0.001665755,0.002696378,0.0007833656,0.00928857,0.005569259,0.003333759,0.009518417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00145549,"about_ca_system_score_gemma":0.001982207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005041794,"about_ca_topic_score_gemma":0.007970613,"domain_scores_codex":[0.9946813,0.001131903,0.0005484197,0.001883097,0.001440016,0.0003152516],"domain_scores_gemma":[0.994489,0.002065634,0.0004058615,0.001485214,0.001219826,0.0003345268],"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":[0.001222546,0.0009526937,0.008500556,0.002064799,0.0003256882,0.000588443,0.0008611041,0.00457361,0.02219459,0.007131713,0.2598849,0.6916993],"study_design_scores_gemma":[0.0007216755,0.001406325,0.01856231,0.0004694794,0.0002474103,0.002650859,0.001803373,0.5415229,0.09625196,0.04552129,0.2905098,0.0003326771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1630262,0.003712638,0.4706752,0.002109875,0.002634571,0.002260414,0.09996145,0.2311225,0.02449733],"genre_scores_gemma":[0.2432757,0.0005882666,0.5775156,0.0006767327,0.0002110512,0.00159038,0.1626951,0.004332701,0.009114507],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01424229,"threshold_uncertainty_score":0.04764521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03571331077631169,"score_gpt":0.3311805450590701,"score_spread":0.2954672342827585,"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."}}