{"id":"W2911338114","doi":"10.1109/access.2019.2891692","title":"Challenging the Boundaries of Unsupervised Learning for Semantic Similarity","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Topic Modeling","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Semantic similarity; Artificial intelligence; Similarity (geometry); Natural language processing; Benchmark (surveying); Sentence; Word (group theory); Unsupervised learning; Mathematics","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":[0.0003756895,0.0000785214,0.000140271,0.00004173522,0.0002267241,0.0003769893,0.001261565,0.00003710733,0.000008024466],"category_scores_gemma":[0.00004839036,0.00005839367,0.00005881061,0.0001315964,0.00004084058,0.0005384375,0.0001977907,0.0001257928,0.000005523349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001214997,"about_ca_system_score_gemma":0.00006202322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007557717,"about_ca_topic_score_gemma":0.00001452735,"domain_scores_codex":[0.999202,0.00003872496,0.0001680662,0.0002247818,0.0001723457,0.0001940802],"domain_scores_gemma":[0.9991933,0.0002011863,0.0000789196,0.0004226315,0.00008262262,0.00002135497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007389708,0.0002129857,0.09182126,0.002039973,0.0002854873,0.000009467337,0.02944801,0.4031201,0.01513591,0.3044347,0.0008900615,0.1525281],"study_design_scores_gemma":[0.0003018463,0.00003191664,0.001813435,0.00003785298,0.000007070001,0.000001725458,0.00008543937,0.9823766,0.006143943,0.006319218,0.002762425,0.0001185239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3683491,0.000103942,0.6294248,0.0009727738,0.0005623238,0.0001963076,3.252918e-7,0.00005184137,0.0003385405],"genre_scores_gemma":[0.9973806,0.000007576984,0.002249343,0.0001713342,0.00006083151,0.00001182042,4.000341e-7,0.000006980847,0.0001110854],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6290315,"threshold_uncertainty_score":0.3635317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04456077407634325,"score_gpt":0.2982622546993254,"score_spread":0.2537014806229822,"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."}}