{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001575038,0.0004236361,0.0004753757,0.002435318,0.0006257205,0.002020127,0.0006265147,0.0007295746,0.001461706],"category_scores_gemma":[0.01283763,0.0003816012,0.0003830719,0.001308345,0.0007734343,0.002522544,0.001086805,0.0008618372,0.0006108641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000302537,"about_ca_system_score_gemma":0.0003707722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008328342,"about_ca_topic_score_gemma":0.0024598,"domain_scores_codex":[0.9986798,0.0004412407,0.0001136907,0.0003836506,0.0002924335,0.00008918592],"domain_scores_gemma":[0.9874232,0.008722924,0.00164704,0.0009372117,0.001027951,0.0002416911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001032717,0.0002414378,0.1581482,0.000870003,0.0001209868,0.0008993134,0.009640862,0.002881147,0.2713674,0.02066911,0.002717277,0.5314116],"study_design_scores_gemma":[0.000157496,0.0005407272,0.4243361,0.0002271603,0.0002937792,0.005041749,0.009127413,0.3160458,0.1368046,0.0814656,0.02569721,0.0002623356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9049428,0.0002006719,0.08927681,0.000136028,0.00002271816,0.00008036692,0.0004522806,0.0008646176,0.004023594],"genre_scores_gemma":[0.9439922,0.0000847671,0.05406886,0.00002642052,0.00001714664,0.00004088244,0.00103591,0.0002200831,0.0005138373],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002435318,"threshold_uncertainty_score":0.00832969,"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."}}