{"id":"W4392669874","doi":"10.18653/v1/2023.ijcnlp-main.39","title":"ProMap: Effective Bilingual Lexicon Induction via Language Model Prompting","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; University of British Columbia","funders":"","keywords":"Lexicon; Computer science; Linguistics; Computational linguistics; Natural language processing; Artificial intelligence; Natural language; Philosophy","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":[0.001797216,0.00194692,0.001660174,0.002136037,0.001411908,0.002529443,0.003003012,0.001222406,0.0254789],"category_scores_gemma":[0.005915307,0.001349197,0.001371698,0.00220574,0.0007301404,0.005919921,0.008582,0.002496421,0.02620137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007066719,"about_ca_system_score_gemma":0.002838574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002155903,"about_ca_topic_score_gemma":0.005125064,"domain_scores_codex":[0.9978235,0.0008852195,0.000155012,0.0005935598,0.0003481965,0.0001945663],"domain_scores_gemma":[0.9967335,0.001566333,0.0001200947,0.000793118,0.000595278,0.0001916677],"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":[0.001010869,0.0004272049,0.00114515,0.0009599783,0.0001376532,0.0008600213,0.0005698023,0.005123333,0.03425697,0.01791046,0.1573522,0.7802464],"study_design_scores_gemma":[0.00152761,0.0006229196,0.001749631,0.0001925191,0.0003221203,0.002089178,0.001343202,0.5280733,0.1321994,0.1441765,0.1874388,0.0002648974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01494687,0.0007063851,0.7878249,0.000710254,0.0007405733,0.0004181787,0.004925265,0.1780524,0.01167517],"genre_scores_gemma":[0.1787558,0.0005520219,0.7686127,0.0006078046,0.0003780678,0.0009071602,0.02823806,0.01177494,0.01017349],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0254789,"threshold_uncertainty_score":0.08523542,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02425201490365063,"score_gpt":0.2873487763397928,"score_spread":0.2630967614361421,"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."}}