{"id":"W1571050549","doi":"10.2307/25148806","title":"Enhancing Information Retrieval Through Statistical Natural Language Processing: A Study of Collocation Indexing1","year":2007,"lang":"en","type":"article","venue":"MIS Quarterly","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Alberta","funders":"","keywords":"Search engine indexing; Collocation (remote sensing); Information retrieval; Computer science; Automatic indexing; Natural language; Natural language processing; Artificial intelligence; Machine learning","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":[0.0007489085,0.0001093563,0.0001489006,0.0001545498,0.0001329187,0.0001796896,0.0003455329,0.00005616978,0.00001115716],"category_scores_gemma":[0.00007595588,0.00009589791,0.00002592009,0.0006614784,0.00003306308,0.002435175,0.00002380472,0.0001800657,0.00003375016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007035613,"about_ca_system_score_gemma":0.0001106893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001215634,"about_ca_topic_score_gemma":0.00005935619,"domain_scores_codex":[0.9982798,0.00004448598,0.0005970714,0.000129585,0.0006906032,0.0002584778],"domain_scores_gemma":[0.9990546,0.0000813712,0.0002200632,0.000235881,0.0003460936,0.00006205299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002313379,0.0004729484,0.0008279145,0.0001684629,0.00001866559,0.00002035451,0.4842599,0.000007727358,0.006871476,0.003748911,0.0001129568,0.5032593],"study_design_scores_gemma":[0.01282163,0.0176465,0.3317883,0.0003425288,0.0001120399,0.0001483894,0.3703456,0.1369941,0.1242786,0.001116914,0.002243728,0.002161633],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5378825,0.00002185808,0.4612919,0.00003235673,0.0001172565,0.0002691706,0.000002640494,0.00006395088,0.0003182797],"genre_scores_gemma":[0.9906399,1.922094e-7,0.009172481,0.00008747944,0.00002715102,0.00000410201,0.00001895212,0.000003411654,0.00004629499],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5010977,"threshold_uncertainty_score":0.3910603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01072236122967445,"score_gpt":0.2951325797756313,"score_spread":0.2844102185459569,"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."}}