{"id":"W2251155774","doi":"10.3115/v1/w14-5708","title":"Multiword noun compound bracketing using Wikipedia","year":2014,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bracketing (phenomenology); Computer science; Natural language processing; Noun; Artificial intelligence; Association (psychology); Meaning (existential); Relation (database); Word (group theory); Linguistics; Psychology; Data mining","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":[0.0004192492,0.0001217338,0.0001285245,0.00008361074,0.0001478599,0.0002843148,0.000813759,0.00006115477,0.00001292778],"category_scores_gemma":[0.0001570539,0.000101715,0.00003713755,0.0002657016,0.00003686069,0.0005932567,0.0003380851,0.0001537977,0.00002817993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003547231,"about_ca_system_score_gemma":0.00002555994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009818686,"about_ca_topic_score_gemma":0.000009462176,"domain_scores_codex":[0.9989918,0.00006081361,0.0001705478,0.0003088659,0.0002103871,0.0002575502],"domain_scores_gemma":[0.9991921,0.0001526686,0.00008433899,0.0004193149,0.00008607944,0.00006550849],"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":[0.000008492852,0.0001058835,0.003106932,0.00009420131,0.00001912449,0.00003871609,0.001179311,0.00004849661,0.1118388,0.3609352,0.002073586,0.5205513],"study_design_scores_gemma":[0.0003121158,0.00005112145,0.0001927583,0.00009635004,0.0000073511,0.00009882183,0.00001650681,0.8702385,0.07146277,0.05118086,0.005779076,0.0005637522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01895996,0.0002099523,0.9743731,0.0002656695,0.0001905233,0.000068699,1.684199e-7,0.001125824,0.004806127],"genre_scores_gemma":[0.4506251,6.94174e-7,0.5487296,0.0004654926,0.00007925486,9.932393e-7,4.518222e-7,0.00000593914,0.00009250807],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.87019,"threshold_uncertainty_score":0.4147819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01868620334993671,"score_gpt":0.2818345594819128,"score_spread":0.2631483561319761,"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."}}