{"id":"W4281391185","doi":"10.3389/frai.2022.796741","title":"Beyond the Benchmarks: Toward Human-Like Lexical Representations","year":2022,"lang":"en","type":"review","venue":"Frontiers in Artificial Intelligence","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Conceptualization; Lexicon; Lexical semantics; Computer science; Natural language processing; Semantics (computer science); Artificial intelligence; Computational semantics; Human language; Lexical item; Process (computing); Key (lock); Word (group theory); Linguistics; Cognitive science; Psychology; Programming language; Operational semantics","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":[0.002063363,0.0005905987,0.00102725,0.00213204,0.0003026022,0.003637296,0.001677463,0.001563461,0.0046263],"category_scores_gemma":[0.005115301,0.0003253378,0.0003639081,0.002731529,0.00243567,0.008800105,0.001558688,0.002168027,0.003801611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008743668,"about_ca_system_score_gemma":0.002131768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001376584,"about_ca_topic_score_gemma":0.00131627,"domain_scores_codex":[0.9993725,0.0002234929,0.00005923841,0.0001002818,0.0002160572,0.00002833251],"domain_scores_gemma":[0.9987256,0.0007970606,0.0000857103,0.0001317503,0.0002184289,0.00004135772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004168548,0.00003131825,0.0001389036,0.004629737,0.00005039332,0.00005781971,0.0002703795,0.0008172973,0.00173345,0.1603815,0.01334864,0.818499],"study_design_scores_gemma":[0.00002237486,0.00005682441,0.0005232891,0.004116679,0.00004774848,0.0003863828,0.0002753409,0.001200754,0.001167881,0.1779483,0.8142192,0.00003516222],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001833589,0.9257188,0.04464007,0.006097266,0.0004943175,0.00004958314,0.0001753749,0.0002248369,0.0207662],"genre_scores_gemma":[0.02901465,0.9197568,0.03993795,0.003339577,0.000599361,0.000137425,0.0005190448,0.0001057249,0.006589483],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.0046263,"threshold_uncertainty_score":0.01547652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1024862600589734,"score_gpt":0.390488722566902,"score_spread":0.2880024625079286,"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."}}