{"id":"W2117424365","doi":"","title":"Learning Noun Phrase Query Segmentation","year":2007,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Query expansion; Web query classification; Query language; Natural language processing; RDF query language; Information retrieval; Artificial intelligence; Precision and recall; Web search query; Noun phrase; Sargable; Query optimization; Segmentation; Phrase; Set (abstract data type); Noun; Search engine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001764943,0.001461308,0.001360351,0.00255479,0.0009095654,0.00168334,0.00208545,0.001607709,0.004453001],"category_scores_gemma":[0.008356786,0.0005799825,0.001203247,0.0022644,0.0009504443,0.004833947,0.001263835,0.001394974,0.004793142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001798163,"about_ca_system_score_gemma":0.002716911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01032968,"about_ca_topic_score_gemma":0.01021331,"domain_scores_codex":[0.9975783,0.0005348501,0.0001939269,0.0009478871,0.000542721,0.0002022113],"domain_scores_gemma":[0.9960024,0.001954478,0.0003258212,0.000390885,0.001186548,0.0001399804],"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":[0.001223808,0.0008117332,0.01734042,0.00122203,0.0002690185,0.0008031325,0.001367993,0.05544667,0.1095561,0.0126512,0.06410027,0.7352076],"study_design_scores_gemma":[0.0001041952,0.0003907371,0.004715692,0.00005155077,0.00009915551,0.0004675289,0.000544894,0.924657,0.04218281,0.01156893,0.01515079,0.00006675308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2505085,0.002030118,0.6917123,0.001063335,0.000262982,0.001148817,0.006863247,0.036269,0.0101416],"genre_scores_gemma":[0.5606602,0.0005080543,0.4041167,0.000647672,0.0001913611,0.0005061697,0.02548356,0.0008227079,0.007063549],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01032968,"threshold_uncertainty_score":0.02053916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0283993285986766,"score_gpt":0.4422297324931074,"score_spread":0.4138304038944308,"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."}}