{"id":"W2200913422","doi":"10.33011/lilt.v9i.1321","title":"Frege in Space: A Program for Compositional Distributional Semantics","year":2014,"lang":"en","type":"article","venue":"Linguistic Issues in Language Technology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":245,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited","keywords":"Principle of compositionality; Meaning (existential); Computer science; Semantics (computer science); Distributional semantics; Lexicon; Lexicology; Linguistics; Syntax; Formal semantics (linguistics); Computational semantics; Lexical semantics; Natural language processing; Cognitive semantics; Artificial intelligence; Space (punctuation); Function (biology); Operational semantics; Lexical item; Programming language; Cognition; Epistemology; Psychology; Philosophy","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003582243,0.0001853761,0.0002945598,0.0005192145,0.00006107172,0.00006600421,0.0009898373,0.0002710069,0.000007607015],"category_scores_gemma":[0.002126886,0.0001828425,0.00004269656,0.0007957228,0.0001735402,0.00007097236,0.0002900114,0.0003733772,0.000006721011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000911824,"about_ca_system_score_gemma":0.00003457654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005879694,"about_ca_topic_score_gemma":0.0000613296,"domain_scores_codex":[0.9985482,0.00004203278,0.0003228652,0.0004542677,0.0001870867,0.0004456259],"domain_scores_gemma":[0.9990383,0.0002092202,0.0001019646,0.0004813946,0.0001347633,0.00003438191],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008144933,0.0001624739,0.001162729,0.00006288374,0.00000412017,0.00008861347,0.0004424581,0.000004508654,0.001157272,0.9790199,0.0001506762,0.01773618],"study_design_scores_gemma":[0.001037207,0.000377627,0.0003131863,0.0003331986,0.000008470178,0.0001010476,0.0001036592,0.05623857,0.02826937,0.9001968,0.01250623,0.0005146547],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02089136,0.004796547,0.9622483,0.006788679,0.0004563272,0.001041607,0.00003565065,0.002759294,0.0009822702],"genre_scores_gemma":[0.5400058,0.000003190961,0.4596078,0.00006464236,0.000100119,0.0001345107,0.00003955916,0.000008571817,0.00003586533],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5191144,"threshold_uncertainty_score":0.7456103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005157375645620031,"score_gpt":0.3124737237818904,"score_spread":0.3073163481362703,"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."}}