{"id":"W1564649749","doi":"10.1007/11424918_40","title":"Voting Between Multiple Data Representations for Text Chunking","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Voting; Computer science; Phrase; Chunking (psychology); Identification (biology); Focus (optics); Artificial intelligence; Natural language processing; Set (abstract data type); Training set; Condorcet method","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001304461,0.0004519504,0.000483975,0.0007171934,0.0004580411,0.0009070524,0.008845273,0.0003128246,0.000005723528],"category_scores_gemma":[0.0007539637,0.0004248419,0.00009577883,0.000567636,0.0003784197,0.001626319,0.004338809,0.0007938281,0.00001029844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000228576,"about_ca_system_score_gemma":0.0003917478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003472273,"about_ca_topic_score_gemma":0.0001324723,"domain_scores_codex":[0.9957947,0.00002514392,0.0005921753,0.002130152,0.0007899354,0.0006679504],"domain_scores_gemma":[0.9949386,0.001600311,0.000429206,0.002617261,0.0002906029,0.0001240136],"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":[0.000001745644,0.000009456245,0.0002176423,0.00004173134,0.000009651474,0.00001186759,0.000321586,0.001230542,0.0001211984,0.01237361,0.00007550952,0.9855855],"study_design_scores_gemma":[0.0002574987,0.00006311993,0.0000760436,0.0005828053,0.0000179397,0.00003177005,1.488331e-7,0.8155689,0.003530985,0.1758107,0.003289325,0.0007707601],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000009431539,0.001308207,0.9951344,0.001327657,0.0005411206,0.0006350991,0.00004475415,0.0005611932,0.0004381548],"genre_scores_gemma":[0.07997935,0.000009636386,0.9177622,0.0006223043,0.001303898,0.00001411772,0.00006969625,0.00003897621,0.0001998125],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9848147,"threshold_uncertainty_score":0.9998204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05162627353109531,"score_gpt":0.3291894077007173,"score_spread":0.2775631341696219,"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."}}