{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T05:13:46Z","timestamp":1748409226895,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095479","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Question Answering System with Sparse and Noisy Feedback"],"prefix":"10.1109","author":[{"given":"Djallel","family":"Bouneffouf","sequence":"first","affiliation":[{"name":"IBM Thomas J. Watson Research Center,Yorktown Heights,NY,USA"}]},{"given":"Oznur","family":"Alkan","sequence":"additional","affiliation":[{"name":"United Health Group"}]},{"given":"Raphael","family":"Feraud","sequence":"additional","affiliation":[{"name":"Orange Labs"}]},{"given":"Baihan","family":"Lin","sequence":"additional","affiliation":[{"name":"Columbia University"}]}],"member":"263","reference":[{"key":"ref13","first-page":"208","article-title":"Contextual bandits with linear payoff functions","volume":"15","author":"chu","year":"2011","journal-title":"AISTATS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/560108"},{"key":"ref15","article-title":"Corrupt bandits","author":"gajane","year":"2016","journal-title":"EWRL"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/481"},{"article-title":"Linear bandits with stochastic delayed feedback","year":"2018","author":"vernade","key":"ref20"},{"key":"ref11","article-title":"Linearizing contextual bandits with latent state dynamics","author":"nelson","year":"2022","journal-title":"Conference on Uncertainty in Artificial Intelligence"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.625"},{"article-title":"Survey on applications of neurosymbolic artificial intelligence","year":"2022","author":"aggarwal","key":"ref10"},{"key":"ref21","article-title":"Learning in generalized linear contextual bandits with stochastic delays","volume":"32","author":"zhou","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1016\/0196-8858(85)90002-8","article-title":"Asymptotically efficient adaptive allocation rules","volume":"6","author":"lai","year":"1985","journal-title":"Advances in Applied Mathematics"},{"key":"ref17","article-title":"A story of two streams: Reinforcement learning models from human behavior and neuropsychiatry","author":"lin","year":"2020","journal-title":"Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems AAMAS ’20"},{"key":"ref16","first-page":"833","article-title":"Best arm identification in multi-armed bandits with delayed feedback","volume":"84","author":"grover","year":"2018","journal-title":"AISTATS"},{"key":"ref19","article-title":"Stochastic bandit models for delayed conversions","author":"vernade","year":"2017","journal-title":"Conference on Uncertainty in Artificial Intelligence"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-31750-2_12"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"ref7","first-page":"127","article-title":"Thompson sampling for contextual bandits with linear payoffs","author":"agrawal","year":"2013","journal-title":"ICML (3)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CEC48606.2020.9185782"},{"key":"ref4","first-page":"374","article-title":"A neural networks committee for the contextual bandit problem","author":"allesiardo","year":"2014","journal-title":"Neural Information Processing - 21st International Conference ICONIP 2014 Kuching Malaysia November 3-6 2014 Proceedings Part I"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.02.052"},{"article-title":"Dynamic bandits with an auto-regressive temporal structure","year":"2022","author":"chen","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110483"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095479.pdf?arnumber=10095479","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:29Z","timestamp":1700507249000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095479\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095479","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}