{"id":"W2887005207","doi":"10.18653/v1/w18-3012","title":"Unsupervised Random Walk Sentence Embeddings: A Strong but Simple Baseline","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Random walk; Sentence; Hyperparameter; Word (group theory); Computer science; Simple (philosophy); Artificial intelligence; Similarity (geometry); Baseline (sea); Natural language processing; Mathematics; Statistics","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":[0.0005334966,0.000147635,0.000180474,0.00007311469,0.0001486014,0.0001543556,0.00089401,0.00004832882,0.0003463498],"category_scores_gemma":[0.0001325816,0.0001222745,0.00006763413,0.0002385805,0.00005361857,0.0004826464,0.0003532424,0.00009859228,0.0002219164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003099387,"about_ca_system_score_gemma":0.00006267381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000312371,"about_ca_topic_score_gemma":0.0000663252,"domain_scores_codex":[0.9984576,0.00006913045,0.0002832219,0.0004957899,0.0003027777,0.0003914616],"domain_scores_gemma":[0.9987498,0.0001343089,0.00004921394,0.0007577498,0.0001737186,0.00013521],"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":[0.0002967596,0.000574878,0.008775639,0.0001386452,0.0002132081,0.0001769511,0.009547492,0.003922609,0.04817095,0.2422099,0.03101859,0.6549543],"study_design_scores_gemma":[0.001150163,0.00004885758,0.00007118573,0.00001257842,0.00000411996,0.000011962,0.0001246753,0.9880151,0.005117298,0.001391445,0.003879967,0.0001727068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07266808,0.00002653871,0.9208746,0.0009188387,0.0002830785,0.0001486247,0.000001699004,0.000323381,0.004755172],"genre_scores_gemma":[0.8518442,0.000003934882,0.145648,0.001051943,0.0003006969,0.000008530605,0.000001831932,0.000008439426,0.001132479],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9840924,"threshold_uncertainty_score":0.498621,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02419813467637873,"score_gpt":0.2657650794472218,"score_spread":0.2415669447708431,"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."}}