{"id":"W2066553323","doi":"10.3115/1631850.1631855","title":"Automatically distinguishing literal and figurative usages of highly polysemous verbs","year":2005,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Principle of compositionality; Literal and figurative language; Computer science; Natural language processing; Semantics (computer science); Meaning (existential); Literal (mathematical logic); Distributional semantics; Artificial intelligence; Verb; Property (philosophy); Linguistics; Polysemy; Programming language; Psychology","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":[0.0001528898,0.00009933659,0.0001425283,0.00006694468,0.00005603508,0.0001814794,0.0004505228,0.00004495475,0.000009836427],"category_scores_gemma":[0.000216897,0.00007424165,0.0000241649,0.0001744271,0.00005955978,0.0006641313,0.0002348407,0.0001010099,0.000002830174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002086602,"about_ca_system_score_gemma":0.00002382985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000362809,"about_ca_topic_score_gemma":0.000007684141,"domain_scores_codex":[0.9992252,0.00003131961,0.0002017854,0.0002106526,0.0001751361,0.000155913],"domain_scores_gemma":[0.9994273,0.0001309808,0.00008484113,0.0002209714,0.00008301604,0.00005292291],"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":[0.00000784263,0.00008190299,0.0006895069,0.0001076174,0.00002273418,0.00003088636,0.006951683,0.000003092026,0.03485531,0.4148844,0.001334586,0.5410305],"study_design_scores_gemma":[0.0006632619,0.0004136967,0.005630511,0.0005175789,0.00002417484,0.0001581703,0.00008648491,0.1909816,0.6882256,0.1108695,0.001542088,0.0008873441],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1133626,0.00263994,0.8695077,0.004501814,0.00006944422,0.0001794825,0.000003730653,0.001456321,0.00827897],"genre_scores_gemma":[0.5227577,0.000001900586,0.4768184,0.0001721611,0.00002418624,0.000001487082,3.796083e-7,0.000002598521,0.0002211737],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6533703,"threshold_uncertainty_score":0.3027486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00932501758208123,"score_gpt":0.2733698065967666,"score_spread":0.2640447890146854,"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."}}