{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002487961,0.001828741,0.001349672,0.001540923,0.0005161564,0.00156811,0.002243807,0.002375328,0.006118981],"category_scores_gemma":[0.009252513,0.000640406,0.0008939114,0.001203181,0.0006095382,0.005168251,0.002136376,0.002399933,0.006248846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005566329,"about_ca_system_score_gemma":0.00111011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00141838,"about_ca_topic_score_gemma":0.003446711,"domain_scores_codex":[0.9976928,0.0008383841,0.0001290636,0.0008164776,0.0003956594,0.0001276644],"domain_scores_gemma":[0.9962949,0.001175123,0.0002279967,0.001456904,0.0006452854,0.0001997808],"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":[0.0008098442,0.001004905,0.003533872,0.0007051242,0.0004484738,0.0001637289,0.0002087865,0.04956678,0.03092914,0.03028817,0.02716889,0.8551723],"study_design_scores_gemma":[0.0001033631,0.0005541907,0.002333437,0.00006632981,0.0001130618,0.0004030032,0.00005206291,0.9182788,0.01461354,0.0429549,0.02043737,0.000090035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02549356,0.001642384,0.9527997,0.0007460498,0.0004568438,0.0002532006,0.001557992,0.009972588,0.007077628],"genre_scores_gemma":[0.4326979,0.000905084,0.5437454,0.0008255049,0.0005957016,0.0005801117,0.006537931,0.001414522,0.01269774],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006118981,"threshold_uncertainty_score":0.02047002,"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."}}