{"id":"W2002586403","doi":"10.3115/1067807.1067851","title":"Bootstrapping statistical parsers from small datasets","year":2003,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":156,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Defense Advanced Research Projects Agency; Johns Hopkins University; National Science Foundation","keywords":"Bootstrapping (finance); Parsing; Computer science; Strapping; Domain (mathematical analysis); Artificial intelligence; Natural language processing; Statistical analysis; Statistics","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":[0.0001398168,0.0000953882,0.00009261511,0.00003838728,0.00005626453,0.0001706414,0.0005987063,0.00004642409,0.000117016],"category_scores_gemma":[0.0001373113,0.00007894725,0.00001582362,0.0001404431,0.00003017731,0.0002680926,0.0001058738,0.0001260609,0.00004394376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001844563,"about_ca_system_score_gemma":0.00004517935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001434327,"about_ca_topic_score_gemma":0.00002322734,"domain_scores_codex":[0.9991557,0.00005264157,0.0001306203,0.000316493,0.0001372673,0.0002072634],"domain_scores_gemma":[0.9993017,0.0001224517,0.00003261696,0.0004416072,0.00001965859,0.00008192042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001647067,0.00003267506,0.0001996889,0.00000676171,0.00001119935,0.00009722073,0.00008936488,0.000001629919,0.002451607,0.9544867,0.01317894,0.02944259],"study_design_scores_gemma":[0.0004550281,0.00007801158,0.0004667819,0.00005968317,0.00001615955,0.00004829922,0.00005663876,0.01503564,0.1396746,0.7899222,0.05338047,0.0008064393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005377295,0.0003903594,0.9960235,0.0001492872,0.00008874443,0.00005623473,0.00004685708,0.0005281965,0.002179067],"genre_scores_gemma":[0.1892583,0.000003197147,0.8100064,0.0006154575,0.00001090051,0.000003587705,0.00004660749,0.000004383515,0.00005118525],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1887206,"threshold_uncertainty_score":0.3219376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0253997854399811,"score_gpt":0.2756000191421251,"score_spread":0.250200233702144,"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."}}