{"id":"W2997405211","doi":"10.1609/aaai.v34i05.6230","title":"Modelling Sentence Pairs via Reinforcement Learning: An Actor-Critic Approach to Learn the Irrelevant Words","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Reinforcement learning; Sentence; Computer science; Artificial intelligence; Natural language processing; Task (project management); Representation (politics); Paraphrase; Inference; Parsing; Similarity (geometry); Machine learning","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":[0.0007806389,0.0003314357,0.0003241248,0.00009027751,0.0004329654,0.0004784148,0.003763327,0.00009359379,0.00002025274],"category_scores_gemma":[0.0004337294,0.0002250099,0.0001424819,0.0008507233,0.0001942066,0.0006248336,0.000813761,0.0007537545,0.00007623785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000642684,"about_ca_system_score_gemma":0.0001099646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001113844,"about_ca_topic_score_gemma":0.00000223204,"domain_scores_codex":[0.9968345,0.00005408739,0.0007194381,0.0008870241,0.0009270662,0.0005778439],"domain_scores_gemma":[0.9982303,0.00009831986,0.0003087175,0.0005056455,0.000566394,0.0002906068],"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":[0.00006028691,0.00009564168,0.0000543571,0.00005931375,0.00001604365,4.967342e-7,0.01479695,0.5179493,0.01082505,0.4193957,0.00003671072,0.03671018],"study_design_scores_gemma":[0.00002265867,0.0002812147,0.000005043535,0.00009746562,0.00001206737,0.000003768376,0.002739257,0.9440281,0.03641832,0.01596051,0.0001692698,0.0002622972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04086315,0.0000149457,0.9447226,0.008965997,0.0002333007,0.0006322426,5.961267e-7,0.00017758,0.004389584],"genre_scores_gemma":[0.9840041,0.00002065945,0.01447002,0.00112321,0.0001511051,0.00004759048,5.684328e-7,0.00002176043,0.0001610306],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9431409,"threshold_uncertainty_score":0.9175636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1377292093343042,"score_gpt":0.287427590337229,"score_spread":0.1496983810029248,"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."}}