{"id":"W2099032682","doi":"","title":"Neutralizing Linguistically Problematic Annotations in Unsupervised Dependency Parsing Evaluation","year":2011,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Parsing; Computer science; Dependency (UML); Annotation; Dependency grammar; Artificial intelligence; Natural language processing; Set (abstract data type); Task (project management); Measure (data warehouse); Quality (philosophy); Data mining; Programming language","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":[0.0007860242,0.0001039526,0.0001125396,0.000202885,0.00007027639,0.0001047292,0.0005412587,0.00005925782,0.00005622829],"category_scores_gemma":[0.0004364246,0.0000909717,0.00002636885,0.0005349364,0.00002017048,0.0005263573,0.00009382221,0.0001453062,0.00001355024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006548297,"about_ca_system_score_gemma":0.0001221108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001419138,"about_ca_topic_score_gemma":0.00007947955,"domain_scores_codex":[0.9987688,0.0001094892,0.0003097067,0.0002850867,0.000303028,0.0002239031],"domain_scores_gemma":[0.9992627,0.00006377165,0.00006548855,0.0003148465,0.0002445282,0.00004869901],"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":[0.000007364228,0.0002614592,0.003047082,0.0001489405,0.00001061151,0.00005103105,0.01393122,0.0000413083,0.008079194,0.8486171,0.00006129384,0.1257434],"study_design_scores_gemma":[0.0002381626,0.00004447794,0.002804436,0.0001752207,0.00001099434,0.00001381666,0.00005809349,0.2022645,0.01051346,0.783666,0.000004001381,0.0002068874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01299614,0.0004085736,0.971849,0.0003193641,0.0001199602,0.0005397749,2.544865e-7,0.0006698325,0.0130971],"genre_scores_gemma":[0.5151044,0.000001302846,0.4847536,0.00009004241,0.000007637692,0.00002782533,0.000001024382,0.00000400403,0.00001010049],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5021083,"threshold_uncertainty_score":0.3709718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07206090392163111,"score_gpt":0.3153775708490825,"score_spread":0.2433166669274514,"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."}}