{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002446403,0.001261605,0.0014246,0.0004532821,0.0004073519,0.0008240832,0.002148682,0.001523852,0.002086026],"category_scores_gemma":[0.007785195,0.0006464272,0.0006454342,0.0004179932,0.001035438,0.001724038,0.001111028,0.00244758,0.0004670859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009783603,"about_ca_system_score_gemma":0.001190902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003682915,"about_ca_topic_score_gemma":0.004088295,"domain_scores_codex":[0.9991308,0.0004388735,0.00003873195,0.000205171,0.0001177691,0.00006869898],"domain_scores_gemma":[0.9973732,0.001878022,0.0002145172,0.0001459967,0.0002558733,0.0001323587],"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":[0.0002498334,0.000148091,0.001128245,0.00008933666,0.0001028296,0.0001807659,0.0001675409,0.9277893,0.004070808,0.009749833,0.001575148,0.05474832],"study_design_scores_gemma":[0.000009810585,0.00001805475,0.00003179554,0.000002296894,0.000006263816,0.000006879055,0.000003262172,0.9967424,0.0002831067,0.002776761,0.0001157958,0.000003551183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03038192,0.0002902304,0.9663897,0.0004631385,0.00008443658,0.0001050762,0.0000542772,0.0007606376,0.001470702],"genre_scores_gemma":[0.8364888,0.0001743033,0.1589886,0.0004228963,0.00008190869,0.0003745609,0.0001894905,0.0001403291,0.003139061],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003682915,"threshold_uncertainty_score":0.01293796,"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."}}