{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:21:09Z","timestamp":1771611669830,"version":"3.50.1"},"publisher-location":"Stroudsburg, PA, USA","reference-count":0,"publisher":"Association for Computational Linguistics","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.18653\/v1\/d17-1153","type":"proceedings-article","created":{"date-parts":[[2018,1,18]],"date-time":"2018-01-18T16:54:31Z","timestamp":1516294471000},"page":"1464-1474","source":"Crossref","is-referenced-by-count":21,"title":["Reinforcement Learning for Bandit Neural Machine Translation with\n            Simulated Human Feedback"],"prefix":"10.18653","author":[{"given":"Khanh","family":"Nguyen","sequence":"first","affiliation":[]},{"given":"Hal","family":"Daum\u00e9 III","sequence":"additional","affiliation":[]},{"given":"Jordan","family":"Boyd-Graber","sequence":"additional","affiliation":[]}],"member":"1643","event":{"name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","location":"Copenhagen, Denmark","start":{"date-parts":[[2017,9]]},"end":{"date-parts":[[2017,9]]}},"container-title":["Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing"],"original-title":[],"deposited":{"date-parts":[[2018,1,18]],"date-time":"2018-01-18T16:55:16Z","timestamp":1516294516000},"score":1,"resource":{"primary":{"URL":"http:\/\/aclweb.org\/anthology\/D17-1153"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"references-count":0,"URL":"https:\/\/doi.org\/10.18653\/v1\/d17-1153","relation":{},"subject":[],"published":{"date-parts":[[2017]]}}}