{"id":"W2955002705","doi":"10.3758/s13428-019-01282-6","title":"LADEC: The Large Database of English Compounds","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Bigram; Lexicon; Computer science; Natural language processing; Lexical database; Morpheme; Compound; WordNet; Parsing; Database; Artificial intelligence; Linguistics; Information retrieval; Trigram","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01223302,0.0001208792,0.0002106212,0.0002503017,0.0001718981,0.000193037,0.003124604,0.0000883022,0.00007786659],"category_scores_gemma":[0.001828557,0.00007927068,0.00007692231,0.001196936,0.0001755404,0.0005433194,0.001887625,0.0008846861,0.00002241553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005240573,"about_ca_system_score_gemma":0.0001526791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009085397,"about_ca_topic_score_gemma":0.000005399459,"domain_scores_codex":[0.9958351,0.001983899,0.0002562639,0.0004250037,0.0009566222,0.000543091],"domain_scores_gemma":[0.9957126,0.001274113,0.00008360219,0.001753451,0.001081008,0.00009519768],"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":[0.00003860363,0.0007427862,0.01077944,0.0002413661,0.00002578068,0.00006240768,0.007028436,4.022865e-7,0.4152699,0.2771238,0.00985751,0.2788295],"study_design_scores_gemma":[0.0007788124,0.0003862278,0.003428209,0.0002100723,0.00001857746,0.00002246152,0.000768249,0.00208506,0.889877,0.01291385,0.08903513,0.0004764079],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06876929,0.006688907,0.91404,0.0006229797,0.00121842,0.002062044,0.00005662844,0.0008692185,0.005672541],"genre_scores_gemma":[0.1678437,0.00002147541,0.8312983,0.00005187705,0.00007156962,0.00009027324,0.000006374844,0.0000147583,0.000601705],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.474607,"threshold_uncertainty_score":0.5806343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1568235960596101,"score_gpt":0.5424968809298324,"score_spread":0.3856732848702222,"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."}}