{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004115941,0.0003351475,0.0003719275,0.0005749072,0.0002468059,0.0003637788,0.000992617,0.0002400184,0.00001441745],"category_scores_gemma":[0.001896749,0.0002830808,0.0001001175,0.002014511,0.0000894193,0.001441344,0.0003885364,0.001469047,0.000008771154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003093199,"about_ca_system_score_gemma":0.0001133174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004958829,"about_ca_topic_score_gemma":0.00002396335,"domain_scores_codex":[0.9967754,0.0005400935,0.0006450539,0.000763454,0.0005206119,0.0007553805],"domain_scores_gemma":[0.9983721,0.0006687827,0.0002978801,0.0003612749,0.0001496522,0.0001503254],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002431757,0.00004639811,0.001392365,0.00008092116,0.00000460444,0.0002094115,0.005803451,0.00000672341,0.05669859,0.0002652159,0.00002819295,0.9354398],"study_design_scores_gemma":[0.002293121,0.0003747772,0.005034759,0.001183429,0.00004886329,0.0006029982,0.005862141,0.2169114,0.737013,0.02545642,0.002243066,0.002976033],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01491432,0.03962749,0.9425131,0.0004802801,0.000326103,0.0002255342,3.45414e-7,0.001145134,0.0007676853],"genre_scores_gemma":[0.3884385,0.000006830383,0.6104798,0.0007496814,0.0001139284,0.00001021023,0.000004938749,0.00002083149,0.0001752826],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9324638,"threshold_uncertainty_score":0.9999622,"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."}}