{"id":"W2154507487","doi":"10.63317/44fpr4ygd2xg","title":"New Tools for Web-Scale N-grams","year":2010,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Ambiguity; n-gram; Set (abstract data type); Scale (ratio); Natural language processing; Annotation; World Wide Web; Information retrieval; Web resource; Artificial intelligence; Resource (disambiguation); Language model","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":[0.0001327718,0.00007616883,0.00007716497,0.00003758652,0.00005453552,0.0003936962,0.0009041822,0.00007377966,0.00004833379],"category_scores_gemma":[0.00006502964,0.00005738016,0.0000453419,0.0001461135,0.0000133803,0.0007333065,0.000143826,0.0001364951,0.00002569436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006262798,"about_ca_system_score_gemma":0.00007689038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003934034,"about_ca_topic_score_gemma":0.0001409025,"domain_scores_codex":[0.999392,0.000004199258,0.00009367612,0.0002228108,0.0001071154,0.0001802057],"domain_scores_gemma":[0.9993459,0.0000814591,0.00003034605,0.0004041054,0.00005746441,0.00008073638],"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":[0.00000139868,0.000008241293,0.00002120171,0.000005028864,0.00000146492,8.831288e-7,0.00008935148,2.912406e-8,0.09503504,0.2236825,0.01940045,0.6617544],"study_design_scores_gemma":[0.0003377078,0.00009037204,0.00008520221,0.00001212657,0.000004007658,0.00002847935,0.000008562391,0.00718288,0.5280787,0.3249854,0.1388564,0.0003302579],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001872614,0.00008342291,0.9915735,0.001748033,0.0003456236,0.0001639774,7.753832e-7,0.001145875,0.003066155],"genre_scores_gemma":[0.08623694,6.380551e-7,0.910091,0.0005923201,0.0001242872,0.00001451283,0.000001280251,0.000005905441,0.002933068],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6614241,"threshold_uncertainty_score":0.3796422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01365188499041967,"score_gpt":0.2777855487621568,"score_spread":0.2641336637717371,"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."}}