{"id":"W2140060501","doi":"10.1145/1557670.1557680","title":"Query segmentation using conditional random fields","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Conditional random field; Query optimization; Query expansion; Segmentation; Quality (philosophy); Sargable; Data mining; Field (mathematics); Information retrieval; Web query classification; Relational database; Artificial intelligence; Web search query; 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":[],"consensus_categories":[],"category_scores_codex":[0.00008699585,0.00004101377,0.00004240442,0.0000430018,0.00005641254,0.0001331816,0.0002009405,0.00001339825,0.00008509557],"category_scores_gemma":[0.000003587023,0.00003581131,0.00002019214,0.00009653831,0.000005784267,0.0008431729,0.00003853329,0.00002508357,0.00003205125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009217028,"about_ca_system_score_gemma":0.000008374025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008797641,"about_ca_topic_score_gemma":0.000001040197,"domain_scores_codex":[0.9995942,0.00001199222,0.00007615115,0.0001171751,0.0001190502,0.00008146516],"domain_scores_gemma":[0.9998024,0.00001566549,0.00002108484,0.0001263358,0.00001391256,0.0000206096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001327637,0.0001366061,0.0003107019,0.000006824474,0.00002935182,0.00003524805,0.0001959239,0.001604754,0.002151796,0.6632801,0.0393657,0.2928697],"study_design_scores_gemma":[0.002237396,0.00008950444,0.004383834,0.000009700949,0.00001064366,0.00001149052,0.00004405899,0.9086536,0.003589586,0.07637804,0.004318099,0.00027403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003502333,0.000008327646,0.9874475,0.0009123748,0.0001299908,0.00006082408,0.000001166597,0.0000755751,0.007861914],"genre_scores_gemma":[0.7060292,0.000005931079,0.2881915,0.004090075,0.0001191742,0.000002033517,0.00005576434,0.00000172541,0.001504643],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9070489,"threshold_uncertainty_score":0.1460343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02237004621615805,"score_gpt":0.2745286333615625,"score_spread":0.2521585871454045,"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."}}