{"id":"W2904760604","doi":"10.1609/aaai.v33i01.33016188","title":"Enriching Word Embeddings with a Regressor Instead of Labeled Corpora","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Vetenskapsrådet","keywords":"Computer science; Natural language processing; Artificial intelligence; Word (group theory); Lexicon; Task (project management); Embedding; Sentence; SemEval; Word embedding; Analogy; Binary classification; Linguistics; Support vector machine","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":[0.000547224,0.0002416171,0.0003966115,0.000166175,0.00009432485,0.0001540425,0.002327599,0.00009113985,0.00004451998],"category_scores_gemma":[0.0002088903,0.0001655883,0.00009501138,0.0007941381,0.0001797125,0.0005528011,0.0004547752,0.0003537387,0.00004962078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003841095,"about_ca_system_score_gemma":0.0001296543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005145984,"about_ca_topic_score_gemma":0.000007910535,"domain_scores_codex":[0.9977849,0.00001728698,0.0006164486,0.0005668141,0.0006667458,0.0003478225],"domain_scores_gemma":[0.997796,0.0001060699,0.0007786496,0.000509897,0.0007324705,0.00007689001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001158059,0.0001144435,0.002219516,0.0001111409,0.00002478872,6.38895e-7,0.002704682,0.000363842,0.09617044,0.8573362,0.00001920251,0.04081931],"study_design_scores_gemma":[0.0001059988,0.0004271398,0.0003299392,0.001101031,0.00001960454,0.00001112514,0.0009557258,0.2202614,0.6921492,0.08419675,0.00006261075,0.0003795435],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9568776,0.00001893645,0.03266268,0.001211996,0.0003056921,0.0005051432,0.000002244293,0.00007486055,0.0083408],"genre_scores_gemma":[0.9847571,0.00001061786,0.01467416,0.0001189885,0.00003018549,0.00001352452,2.31664e-7,0.00001466831,0.0003805524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7731394,"threshold_uncertainty_score":0.6752494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05268464246031737,"score_gpt":0.2704866470360274,"score_spread":0.2178020045757101,"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."}}