{"id":"W4389009377","doi":"10.18653/v1/2023.inlg-main.1","title":"Guided Beam Search to Improve Generalization in Low-Resource Data-to-Text Generation","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Computer science; Generalization; Decoding methods; Set (abstract data type); Machine learning; Artificial intelligence; Process (computing); Resource (disambiguation); Beam search; Data mining; Algorithm; Search algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.007831682,0.001819475,0.001889387,0.001975328,0.0009577528,0.001490809,0.003136666,0.002621071,0.005231722],"category_scores_gemma":[0.03250359,0.0009659423,0.001128458,0.001419304,0.001419661,0.002763084,0.002597372,0.003299181,0.002071477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001078414,"about_ca_system_score_gemma":0.001588478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004321219,"about_ca_topic_score_gemma":0.00679082,"domain_scores_codex":[0.9966859,0.001826668,0.0001964533,0.0005590157,0.000541808,0.0001902535],"domain_scores_gemma":[0.9797195,0.01587584,0.0004952083,0.002006907,0.001624529,0.0002780427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006370172,0.0004151571,0.00554348,0.0002126426,0.0002699698,0.0003279032,0.0006884666,0.5488022,0.007679148,0.01237087,0.01228631,0.4107669],"study_design_scores_gemma":[0.00006650577,0.0000579979,0.0002109884,0.00001496518,0.00001668855,0.00004452484,0.00003243455,0.9864554,0.001955398,0.01041295,0.0007225029,0.000009616462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03444529,0.0004889357,0.9584568,0.0004695142,0.00007046433,0.0001673733,0.000203605,0.004192601,0.001505459],"genre_scores_gemma":[0.406376,0.000208284,0.5844525,0.001411793,0.0001637095,0.0007605542,0.001936691,0.001292991,0.003397509],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007831682,"threshold_uncertainty_score":0.04141837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06224814578580187,"score_gpt":0.3448637297661659,"score_spread":0.282615583980364,"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."}}