{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001052862,0.000431691,0.000919375,0.000525743,0.0005052524,0.0004653682,0.004917286,0.0002615611,0.0002476456],"category_scores_gemma":[0.0002926365,0.0003244936,0.0003983106,0.002097696,0.0003123053,0.000404476,0.00130831,0.001615266,0.00002476516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003684419,"about_ca_system_score_gemma":0.0003172323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001017506,"about_ca_topic_score_gemma":0.00002923174,"domain_scores_codex":[0.9961998,0.0005529119,0.001097295,0.001002148,0.0006271758,0.0005206602],"domain_scores_gemma":[0.997705,0.0003663196,0.0004272038,0.001361862,0.00005254974,0.00008702408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001299022,0.00004739779,9.105148e-7,0.0003317008,0.00002105338,0.00004899761,0.0005833787,0.00000589636,2.433839e-7,0.09754103,0.01257062,0.8888475],"study_design_scores_gemma":[0.000005129353,0.00003362053,9.115441e-8,0.0005026435,0.00004741975,0.00002248323,0.0002256744,0.001028398,0.00003106594,0.3781219,0.6196206,0.0003610266],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[4.111825e-8,0.6039752,0.3923889,0.0002055165,0.001913713,0.0004913761,0.000008082227,0.0001572112,0.0008599021],"genre_scores_gemma":[0.00001313623,0.8188449,0.1800109,0.0001955251,0.0001893906,0.0004200659,0.00008051718,0.0000313255,0.0002142868],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8884864,"threshold_uncertainty_score":0.9999207,"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."}}