{"id":"W33598619","doi":"","title":"Improving a statistical language model by modulating the effects of context words","year":2008,"lang":"en","type":"article","venue":"UCL Discovery (University College London)","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Feature (linguistics); Word (group theory); Artificial intelligence; Context (archaeology); Feature vector; Language model; Artificial neural network; Context model; Natural language processing; Pattern recognition (psychology); Mathematics; Linguistics","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":[0.00169543,0.001333546,0.0008780592,0.0005895382,0.0003898251,0.001173532,0.001077153,0.0009581466,0.002074807],"category_scores_gemma":[0.007724555,0.0004814824,0.0008382761,0.0006483597,0.0004548528,0.003048364,0.0008424766,0.001804166,0.001637594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000392139,"about_ca_system_score_gemma":0.0008130074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004946063,"about_ca_topic_score_gemma":0.008151547,"domain_scores_codex":[0.9992502,0.0002589742,0.00004199658,0.0002134172,0.0001636628,0.0000715719],"domain_scores_gemma":[0.9971246,0.001972364,0.0001403534,0.0003844523,0.0003148257,0.00006336168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000446879,0.0003751248,0.005049266,0.0001911984,0.000309249,0.0001553342,0.0001294139,0.6139612,0.06006715,0.006094166,0.002656124,0.3105649],"study_design_scores_gemma":[0.000009307129,0.00005403587,0.0003237644,0.000004485824,0.00003831007,0.00002149474,0.000004701036,0.9919458,0.004788616,0.002395627,0.0004014013,0.00001240116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.132075,0.001285985,0.8587791,0.0008385378,0.0002763578,0.0000568098,0.0002563239,0.002956767,0.003475079],"genre_scores_gemma":[0.7803099,0.0009232033,0.2128325,0.0004663666,0.0002860579,0.0001231124,0.0007111902,0.0004677396,0.003879965],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004946063,"threshold_uncertainty_score":0.009834528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006199984077451072,"score_gpt":0.1854097546974772,"score_spread":0.1792097706200262,"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."}}