{"id":"W7132621154","doi":"","title":"Big BiRD: a large, fine-grained, bigram relatedness dataset for examining semantic composition","year":2019,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Bigram; Semantic similarity; Semantics (computer science); Benchmark (surveying); Annotation; Scale (ratio); Meaning (existential)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.001406855,0.000980876,0.0005571978,0.005146919,0.001756025,0.0009431631,0.001274349,0.001598695,0.005209608],"category_scores_gemma":[0.009725839,0.0003187909,0.0009330249,0.004212677,0.0005708457,0.003012233,0.002131646,0.001655348,0.004554918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009003094,"about_ca_system_score_gemma":0.001186265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007252316,"about_ca_topic_score_gemma":0.01912986,"domain_scores_codex":[0.9980304,0.0005263386,0.0002975155,0.0005294448,0.000487391,0.0001288742],"domain_scores_gemma":[0.9951618,0.001787294,0.000548232,0.00115882,0.0009474085,0.0003964866],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001830259,0.001854673,0.05276452,0.007481882,0.0006241955,0.001812824,0.006184881,0.006569788,0.09127545,0.02422048,0.4100316,0.3953494],"study_design_scores_gemma":[0.0005729796,0.001241013,0.1909406,0.0005117147,0.0002609543,0.00349696,0.004681014,0.05194328,0.03646458,0.02314651,0.6863325,0.0004078718],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.3116134,0.003490845,0.09287181,0.001215902,0.0005636924,0.001554703,0.5470737,0.01243861,0.02917733],"genre_scores_gemma":[0.1495757,0.0004307102,0.1519994,0.0003806329,0.00009932466,0.001618816,0.6886886,0.0006111887,0.006595621],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.007252316,"threshold_uncertainty_score":0.0174278,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02076164190976727,"score_gpt":0.2784811732803737,"score_spread":0.2577195313706064,"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."}}