{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000376929,0.0002459662,0.0003406528,0.0001555278,0.00008347814,0.0002227214,0.001820308,0.00007832998,0.00005745216],"category_scores_gemma":[0.0001470049,0.0001727552,0.0001165195,0.0005808275,0.0001354302,0.0003423304,0.0003339452,0.0002649307,0.00003431491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000466741,"about_ca_system_score_gemma":0.0001333681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009908598,"about_ca_topic_score_gemma":0.00001323928,"domain_scores_codex":[0.9977465,0.00002014683,0.0005909862,0.0005813449,0.0006909674,0.000370113],"domain_scores_gemma":[0.9979513,0.0001480882,0.0005387199,0.0005597261,0.0007200019,0.00008215311],"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":[0.0002997173,0.0005044544,0.0224785,0.0003640213,0.00005095387,0.000001583984,0.003302067,0.1280815,0.115956,0.669313,0.00001401194,0.05963418],"study_design_scores_gemma":[0.00004223511,0.0001554888,0.0007125816,0.0005657837,0.000008175223,0.000001222824,0.0002475378,0.6150718,0.3813305,0.001685054,0.00001061715,0.0001689866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7771056,0.000003652352,0.2211145,0.0006512537,0.0002292118,0.0003950856,0.000004072017,0.00005796795,0.0004387156],"genre_scores_gemma":[0.9844991,0.000002578302,0.01519428,0.0001285439,0.00002197869,0.00001360873,3.778466e-7,0.00001504868,0.0001244997],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6676279,"threshold_uncertainty_score":0.7044752,"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."}}