{"id":"W4402671182","doi":"10.18653/v1/2024.acl-srw.34","title":"Homophone2Vec: Embedding Space Analysis for Empirical Evaluation of Phonological and Semantic Similarity","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"McGill University","keywords":"Computer science; Semantic similarity; Embedding; Similarity (geometry); Semantic space; Natural language processing; Space (punctuation); Artificial intelligence; Information retrieval","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002514971,0.001657377,0.001082887,0.002447891,0.0007373488,0.001537944,0.001357563,0.0009492859,0.005913695],"category_scores_gemma":[0.009568872,0.0002953916,0.001081693,0.002732659,0.0006136266,0.002465568,0.001855183,0.00155626,0.00271894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006013365,"about_ca_system_score_gemma":0.00128721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005022704,"about_ca_topic_score_gemma":0.006532711,"domain_scores_codex":[0.9976791,0.0008495423,0.0002066913,0.0005785554,0.0004946926,0.0001914881],"domain_scores_gemma":[0.9963557,0.001813141,0.0001519159,0.0008149504,0.0007177276,0.0001466503],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001365452,0.0008884064,0.02190612,0.0008228885,0.0007862948,0.0002755192,0.0004325828,0.03940406,0.01823538,0.01031266,0.06493887,0.8406317],"study_design_scores_gemma":[0.0001704063,0.0006127286,0.01384735,0.00008310947,0.0001487493,0.0006006517,0.0005665363,0.9313148,0.02512217,0.01622133,0.01120501,0.0001072078],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2266134,0.002014628,0.7242348,0.0004443071,0.0007303274,0.0002435912,0.01540678,0.02678051,0.003531589],"genre_scores_gemma":[0.6446252,0.0005390248,0.3060726,0.0001522588,0.0002031104,0.0005436885,0.04270086,0.001707234,0.003456065],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005913695,"threshold_uncertainty_score":0.01978332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1165663195041532,"score_gpt":0.3838189603201362,"score_spread":0.2672526408159831,"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."}}