{"id":"W2892043975","doi":"10.18653/v1/d18-1502","title":"Dual Fixed-Size Ordinally Forgetting Encoding (FOFE) for Competitive Neural Language Models","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Forgetting; Dual (grammatical number); Computer science; Encoding (memory); Perplexity; Artificial neural network; Word (group theory); Language model; Artificial intelligence; Deep neural networks; Mathematics; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003621971,0.0001532307,0.0001757354,0.00005705474,0.0002365607,0.0001698622,0.0005809847,0.00005494347,0.00003536512],"category_scores_gemma":[0.0001337687,0.0001374673,0.00008675997,0.0001496582,0.00004382526,0.0007284088,0.0003426954,0.0001014772,0.00001783965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003865319,"about_ca_system_score_gemma":0.00004489795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008015137,"about_ca_topic_score_gemma":0.00007936673,"domain_scores_codex":[0.9985901,0.00003514401,0.0002554547,0.0004636909,0.0002146577,0.0004409748],"domain_scores_gemma":[0.9988966,0.0003503839,0.00007896924,0.0004153838,0.0001687744,0.00008987974],"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":[0.00001787194,0.0000374076,0.0001776707,0.00003409442,0.00002939533,0.00002176067,0.008289316,0.001246033,0.006801235,0.9265318,0.0008783663,0.05593505],"study_design_scores_gemma":[0.000362268,0.0001009833,0.00004786758,0.00002153102,0.000005022406,0.00001894902,0.0005391662,0.9876674,0.003992536,0.006620069,0.0004235794,0.0002006585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07007341,0.00002229519,0.8997011,0.0009010163,0.0004604852,0.0002431308,0.000003271148,0.0002893517,0.0283059],"genre_scores_gemma":[0.7262824,4.780109e-7,0.2711498,0.0007938439,0.0004121616,0.00001589289,0.00000136133,0.00001037683,0.001333688],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9864213,"threshold_uncertainty_score":0.5605754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02834280651441331,"score_gpt":0.2765021994500761,"score_spread":0.2481593929356628,"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."}}