{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:01:46Z","timestamp":1761894106246,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819527243","type":"print"},{"value":"9789819527250","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-2725-0_11","type":"book-chapter","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:19:43Z","timestamp":1761887983000},"page":"156-173","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DualReward: A Dynamic Reinforcement Learning Framework for\u00a0Cloze Tests Distractor Generation"],"prefix":"10.1007","author":[{"given":"Tianyou","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinglu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingshen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinying","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiying","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,1]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Alhazmi, E., Sheng, Q.Z., Zhang, W.E., Zaib, M., Alhazmi, A.: Distractor generation in multiple-choice tasks: a survey of methods, datasets, and evaluation. arXiv:2402.01512 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.799"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Chiang, S.-H., Wang, S.-C., Fan, Y.-C.: CDGP: automatic cloze distractor generation based on pre-trained language model. In: Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 5835\u20135840. Springer, Heidelberg (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.429"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Chung, H.L., Chan, Y.H., Fan, Y.C.: A BERT-based distractor generation scheme with multi-tasking and negative answer training strategies. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 4390\u20134400. Springer, Heidelberg (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.393"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Fernandez, N., Scarlatos, A., Feng, W., Woodhead, S., Lan, A.: DiVERT: distractor generation with variational errors represented as text for math multiple-choice questions. arXiv:2406.19356 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.512"},{"key":"11_CR5","unstructured":"Florensa, C., Held, D., Geng, X., Abbeel, P.: Automatic goal generation for reinforcement learning agents. In: International Conference on Machine Learning, pp. 1515\u20131528. Springer, Heidelberg (2018)"},{"key":"11_CR6","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Proceedings of the 35th International Conference on Machine Learning (ICML) (2018)"},{"key":"11_CR7","unstructured":"Hadfield-Menell, D., Milli, S., Abbeel, P., Russell, S.J., Dragan, A.: Inverse reward design. In: Advances in Neural Information Processing Systems (NeurIPS 2017), vol. 30 (2017)"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Jiang, S., Lee, J.S.: Distractor generation for Chinese fill-in-the-blank items. In: Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications, pp. 143\u2013148. Springer, Heidelberg (2017)","DOI":"10.18653\/v1\/W17-5015"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Kumar, A.P., Nayak, A., Shenoy, M., Goyal, S., Chaitanya: A novel approach to generate distractors for multiple choice questions. Expert Syst. Appl. 225, 120022 (2023)","DOI":"10.1016\/j.eswa.2023.120022"},{"key":"11_CR10","unstructured":"Kwon, M., ElSayed-Aly, I., Feng, L.: Adaptive reward design for reinforcement learning in complex robotic tasks. arXiv:2412.10917 (2024)"},{"issue":"181","key":"11_CR11","first-page":"1","volume":"21","author":"S Narvekar","year":"2020","unstructured":"Narvekar, S., Peng, B., Leonetti, M., Sinapov, J., Taylor, M.E., Stone, P.: Curriculum learning for reinforcement learning domains: a framework and survey. J. Mach. Learn. Res. 21(181), 1\u201350 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Panda, S., Gomez, F.P., Flor, M., Rozovskaya, A.: Automatic generation of distractors for fill-in-the-blank exercises with round-trip neural machine translation. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pp. 391\u2013401. Springer, Heidelberg (2022)","DOI":"10.18653\/v1\/2022.acl-srw.31"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Qu, F., Sun, H., Wu, Y.: Unsupervised distractor generation via large language model distilling and counterfactual contrastive decoding. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 827\u2013838. Springer, Heidelberg (2024)","DOI":"10.18653\/v1\/2024.findings-acl.47"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Ren, S., Zhu, K.Q.: Knowledge-driven distractor generation for cloze-style multiple choice questions. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 5, pp. 4339\u20134347 (2021)","DOI":"10.1609\/aaai.v35i5.16559"},{"key":"11_CR15","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv:1707.06347 (2017)"},{"key":"11_CR16","unstructured":"Taslimipoor, S., Benedetto, L., Felice, M., Buttery, P.: Distractor generation using generative and discriminative capabilities of transformer-based models. In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 5052\u20135063. Springer, Heidelberg (2024)"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Wang, J., Y. Liu, and B. Li.: Reinforcement learning with perturbed rewards. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 6202\u20136209 (2020)","DOI":"10.1609\/aaai.v34i04.6086"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Wang, H.J., et al.: Distractor generation based on Text2Text language models with pseudo Kullback-Leibler divergence regulation. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 12477\u201312491. Springer, Heidelberg (2023)","DOI":"10.18653\/v1\/2023.findings-acl.790"},{"key":"11_CR19","unstructured":"Xu, Z., van Hasselt, H.P., Silver, D.: Meta-gradient reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 31, pp. 2396\u20132407. Springer, Heidelberg (2018)"},{"key":"11_CR20","unstructured":"Yeung, C.Y., Lee, J.S., Tsou, B.K.: Difficulty-aware distractor generation for gap-fill items. In: Proceedings of the 17th Annual Workshop of the Australasian Language Technology Association, pp. 159\u2013164. Springer, Heidelberg (2019)"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Yu, H.C., et al.: Enhancing distractor generation for multiple-choice questions with retrieval augmented pretraining and knowledge graph integration. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 11019\u201311029. Springer, Heidelberg (2024)","DOI":"10.18653\/v1\/2024.findings-acl.655"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Zesch, T., Melamud, O.: Automatic generation of challenging distractors using context-sensitive inference rules. In: Proceedings of the Ninth Workshop on Innovative Use of NLP for Building Educational Applications, pp. 143\u2013148. Springer, Heidelberg (2014)","DOI":"10.3115\/v1\/W14-1817"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, X., Lapata, M.: Sentence simplification with deep reinforcement learning. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 584\u2013594. Springer, Heidelberg (2017)","DOI":"10.18653\/v1\/D17-1062"},{"key":"11_CR24","unstructured":"Zheng, Z., Oh, J., Singh, S.: On learning intrinsic rewards for policy gradient methods. In: Advances in Neural Information Processing Systems (NeurIPS 2018), vol. 31 (2018)"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Mita, M., Komachi, M.: ClozEx: a task toward generation of English cloze explanation. In: Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 5228\u20135242. Springer, Heidelberg (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.347"}],"container-title":["Lecture Notes in Computer Science","Chinese Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-2725-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:19:52Z","timestamp":1761887992000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-2725-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"ISBN":["9789819527243","9789819527250"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-2725-0_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,1]]},"assertion":[{"value":"1 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China National Conference on Chinese Computational Linguistics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jinan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cncl2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/link.springer.com\/conference\/cncl","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}