{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00152781,0.001238472,0.001246248,0.006238834,0.001356615,0.00203073,0.001469013,0.001154886,0.007290996],"category_scores_gemma":[0.007167073,0.0005374354,0.0010757,0.003978637,0.0004857037,0.005972495,0.003093773,0.000945661,0.005536293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005950012,"about_ca_system_score_gemma":0.001677167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006571673,"about_ca_topic_score_gemma":0.008495467,"domain_scores_codex":[0.9968575,0.0006020084,0.0002892835,0.001215358,0.0008814926,0.0001543393],"domain_scores_gemma":[0.995779,0.001583895,0.0004737678,0.0008854661,0.001063776,0.0002140681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005962076,0.0003661851,0.009039404,0.001133381,0.0003264021,0.001407723,0.001383755,0.01148699,0.0523022,0.01023228,0.02026953,0.891456],"study_design_scores_gemma":[0.0001062149,0.0005978758,0.01717276,0.0002443376,0.0002642391,0.004815286,0.003037403,0.6500003,0.1569774,0.04937554,0.1171041,0.0003045895],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1777601,0.001683101,0.7648177,0.0004505926,0.0005337549,0.0008717128,0.005185735,0.03804019,0.01065703],"genre_scores_gemma":[0.2930202,0.0004619111,0.6799642,0.0001233624,0.00009456587,0.0002288663,0.01549504,0.001392645,0.009219162],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007290996,"threshold_uncertainty_score":0.02439082,"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."}}