{"id":"W4229005744","doi":"10.18653/v1/2022.naacl-main.257","title":"Learning to Transfer Prompts for Text Generation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","topic":"Topic Modeling","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Renmin University of China; National Natural Science Foundation of China","keywords":"Computational linguistics; Computer science; Natural language processing; Linguistics; Artificial intelligence; Association (psychology); Cognitive science; Philosophy; Psychology; Epistemology","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":[0.002931245,0.001678226,0.00104951,0.001405899,0.000901951,0.001255843,0.002171142,0.001819533,0.02110636],"category_scores_gemma":[0.01769433,0.000607743,0.0007820611,0.0009788381,0.0007320156,0.005089655,0.003498132,0.00292162,0.01195923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007194445,"about_ca_system_score_gemma":0.001425417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001202377,"about_ca_topic_score_gemma":0.001832912,"domain_scores_codex":[0.9979327,0.0008361891,0.0001093407,0.0007156426,0.0002349297,0.0001712354],"domain_scores_gemma":[0.9924067,0.00482651,0.0002347446,0.001224286,0.0009544449,0.0003533685],"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":[0.001137523,0.0004411326,0.001280211,0.000308137,0.0000407593,0.000181334,0.0003555969,0.01313251,0.008147239,0.009661951,0.05268065,0.9126331],"study_design_scores_gemma":[0.0004700035,0.0004712013,0.0007085947,0.00008063581,0.00007634437,0.0001856589,0.0003207168,0.8569023,0.01948575,0.09998628,0.02125816,0.00005432556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03669969,0.001280465,0.8896211,0.001503662,0.001832997,0.0006918731,0.00203023,0.05787953,0.008460503],"genre_scores_gemma":[0.5371673,0.0005725134,0.43894,0.0007977533,0.0007814942,0.0012052,0.005769028,0.001711819,0.01305495],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02110636,"threshold_uncertainty_score":0.07060784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02267813460258396,"score_gpt":0.2531906426618575,"score_spread":0.2305125080592736,"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."}}