{"id":"W86816073","doi":"","title":"A distributional account of the semantics of multiword expressions","year":2008,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Lexicon; Natural language processing; Artificial intelligence; Meaning (existential); Semantics (computer science); Homogeneous; Distributional semantics; Relation (database); Linguistics; Mathematics; Semantic similarity; Psychology; Philosophy; Programming language; Database","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":[0.00006200546,0.00004666782,0.00007442789,0.000017865,0.00006314686,0.000005030959,0.0007275549,0.00003165301,0.00001913737],"category_scores_gemma":[0.00008921379,0.000025906,0.00004621563,0.0002405231,0.0001011017,0.0001315177,0.0004362067,0.00006816845,0.00000106516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001066267,"about_ca_system_score_gemma":0.00004944404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003269145,"about_ca_topic_score_gemma":0.000001957023,"domain_scores_codex":[0.9994588,0.00001695,0.0001344846,0.00009130286,0.0002247257,0.00007376355],"domain_scores_gemma":[0.9994074,0.00004858148,0.0000935185,0.0003364919,0.00009883748,0.00001517041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001320809,0.0004865662,0.02987858,0.00009065891,0.0000295723,0.00001314787,0.001781451,0.00004567586,0.404489,0.5261638,0.02758491,0.009423487],"study_design_scores_gemma":[0.0001199326,0.00001702931,0.009732663,0.00007216975,0.000003267363,0.0000336773,0.000008313054,0.00578233,0.9670113,0.01647918,0.0006485812,0.00009153584],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06993656,0.0002050222,0.9284218,0.0007709251,0.0000702648,0.00008555587,0.000009002429,0.0001100058,0.0003908742],"genre_scores_gemma":[0.7081998,0.000003550334,0.2916442,0.00004043645,0.000005024452,0.000001653409,4.577545e-7,0.000001234713,0.0001036499],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6382632,"threshold_uncertainty_score":0.135199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01646161670868186,"score_gpt":0.2579161318845242,"score_spread":0.2414545151758423,"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."}}