{"id":"W2903988268","doi":"10.1609/aaai.v33i01.33017031","title":"Fast PMI-Based Word Embedding with Efficient Use of Unobserved Patterns","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Pointwise mutual information; Word (group theory); Computer science; Word embedding; Artificial intelligence; Embedding; Similarity (geometry); Pointwise; Margin (machine learning); Natural language processing; Semantic similarity; Kernel (algebra); Latent semantic analysis; Vocabulary; Mutual information; Machine learning; 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":[0.0007979315,0.001050449,0.001160912,0.001434935,0.0004785105,0.0008888202,0.001738622,0.0009151755,0.002996642],"category_scores_gemma":[0.004612943,0.000559232,0.0009612756,0.001997447,0.0006901576,0.003090106,0.001878596,0.001802975,0.002319344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000571879,"about_ca_system_score_gemma":0.001053258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002214719,"about_ca_topic_score_gemma":0.003985354,"domain_scores_codex":[0.9991047,0.0002424808,0.00007301119,0.0002581258,0.0002449748,0.0000766409],"domain_scores_gemma":[0.9979262,0.000972032,0.0001857069,0.000437884,0.0003962136,0.00008182642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002433074,0.0001833838,0.002005999,0.0002258003,0.0001012832,0.0001292846,0.0002384502,0.1141129,0.01634219,0.02173503,0.006426656,0.8382556],"study_design_scores_gemma":[0.00001304544,0.00004633222,0.0003334196,0.000006829109,0.000008240259,0.00006667343,0.00002957507,0.9820326,0.003314413,0.01293201,0.001204236,0.00001264836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01222813,0.0001598366,0.9857136,0.00009113055,0.00004062758,0.00005337879,0.0001518742,0.001100438,0.0004610826],"genre_scores_gemma":[0.2320499,0.0002494625,0.7599489,0.0001222393,0.0001049613,0.0003894652,0.00222497,0.0004057873,0.004504405],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002996642,"threshold_uncertainty_score":0.01002479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09438551158186712,"score_gpt":0.2798486501070082,"score_spread":0.185463138525141,"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."}}