{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T12:21:26Z","timestamp":1726230086248},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031434112"},{"type":"electronic","value":"9783031434129"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43412-9_8","type":"book-chapter","created":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T16:28:38Z","timestamp":1694881718000},"page":"131-146","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adversarial Imitation Learning with\u00a0Controllable Rewards for\u00a0Text Generation"],"prefix":"10.1007","author":[{"given":"Keizaburo","family":"Nishikino","sequence":"first","affiliation":[]},{"given":"Kenichi","family":"Kobayashi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,17]]},"reference":[{"key":"8_CR1","unstructured":"Kaplan, J., et al.: Scaling Laws for Neural Language Models (2020), arXiv:2001.08361"},{"key":"8_CR2","unstructured":"I. Solaiman, M. Brundage, J. Clark, A. Askell, A. Herbert-Voss, J. Wu, A. Radford, G. Krueger, J. W. Kim, S. Kreps, M. McCain, A. Newhouse, J. Blazakis, K. McGuffie, and J. Wang, \"Release Strategies and the Social Impacts of Language Models,\" 2019, arXiv:1908.09203"},{"key":"8_CR3","unstructured":"Brown, T.B., et al.: Language Models are Few-Shot Learners (2020), arXiv:2005.14165"},{"key":"8_CR4","unstructured":"Holtzman, A., Buys, J., Du, L., Forbes, M., Choi, Y.: The curious case of neural text degeneration. Presented at the International Conference on Learning Representations (2020)"},{"key":"8_CR5","unstructured":"Welleck, S., Kulikov, I., Roller, S., Dinan, E., Cho, K., Weston, J.: Neural Text Generation With Unlikelihood Training. Presented at the International Conference on Learning Representations (2020)"},{"key":"8_CR6","unstructured":"Ouyang, L.: Training language models to follow instructions with human feedback. In: Advances in Neural Information Processing Systems (2022)"},{"key":"8_CR7","unstructured":"Stiennon, N., et al.: Learning to summarize with human feedback. In Advances in Neural Information Processing Systems 33, pp. 3008\u20133021 (2020)"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Torabi, F., Warnell, G., Stone, P.: Recent Advances in Imitation Learning from Observation In: Proceedings of 28th International Joint Conference on Artificial Intelligence, pp. 6325\u20136331 (2019)","DOI":"10.24963\/ijcai.2019\/882"},{"key":"8_CR9","unstructured":"Zhou, W., Ge, T., Xu, K., Wei, F., Zhou, M.: Self-Adversarial Learning with Comparative Discrimination for Text Generation. In: International Conference on Learning Representations (2020)"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Wu, Q., Li, L., Yu, Z.: TextGAIL: generative adversarial imitation learning for text generation. In: Proceedings of AAAI Conference on Artificial Intelligence, vol. 35(16), pp. 14067\u201314075 (2021)","DOI":"10.1609\/aaai.v35i16.17656"},{"key":"8_CR11","unstructured":"Lamprier, S., et al.: Generative cooperative networks for natural language generation. In: Proceedings of 39th International Conference on Machine Learning, vol. 162, pp. 11891\u201311905. PMLR (2022)"},{"key":"8_CR12","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Lin, K., Li, D., He, X., Zhang, Z., Sun, M.: Adversarial Ranking for Language Generation. In Advances in Neural Information Processing Systems, vol. 30 (2017)","DOI":"10.18653\/v1\/D17-1230"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Guo, J., Lu, S., Cai, H., Zhang, W., Yu, Y., Wang, J.: Long text generation via adversarial training with leaked information. In: Proceedings of AAAI Conference on Artificial Intelligence, vol. 32(1) (2018)","DOI":"10.1609\/aaai.v32i1.11957"},{"key":"8_CR15","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal Policy Optimization Algorithms, arXiv:1707.06347 (2017)"},{"key":"8_CR16","unstructured":"Ho, J., Ermon, S.: Generative Adversarial Imitation Learning. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"issue":"1","key":"8_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2307\/1913641","volume":"46","author":"T Kloek","year":"1978","unstructured":"Kloek, T., van Dijk, H.K.: Bayesian estimates of equation system parameters: an application of integration by Monte Carlo. Econometrica 46(1), 1\u201319 (1978)","journal-title":"Econometrica"},{"key":"8_CR18","unstructured":"Fu, J., Luo, K., Levine, S.: Learning robust rewards with adverserial inverse reinforcement learning. In: International Conference on Learning Representations (2018)"},{"key":"8_CR19","unstructured":"Ghasemipour, S.K.S., Zemel, R.S., Gu, S.: A divergence minimization perspective on imitation learning methods, In: 3rd Annual Conference on Robot Learning, Proceedings of Machine Learning Research, vol. 100, pp. 1259\u20131277. PMLR (2019)"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Zhao, M., Cong, Y., Dai, S., Carin, L.: Bridging maximum likelihood and adversarial learning via $$\\alpha $$-divergence. In: Proceedings of AAAI Conference on Artificial Intelligence, vol. 34(04), pp. 6901\u20136908 (2020)","DOI":"10.1609\/aaai.v34i04.6172"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Nat. Academy Sci. 114(13), 3521\u20133526 (2017)","DOI":"10.1073\/pnas.1611835114"},{"key":"8_CR22","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: The 32nd International Conference on Machine Learning, In Proc. Machine Learning Research, vol. 37, pp. 1889\u20131897. PMLR (2015)"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Lin, B.Y., et al.: CommonGen: a constrained text generation challenge for generative commonsense reasoning. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 1823\u20131840. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.165"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Mostafazadeh, N., et al.: A corpus and cloze evaluation for deeper understanding of commonsense stories. In: Proceedings of 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 839\u2013849. Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/N16-1098"},{"key":"8_CR25","unstructured":"Wu, Y., et al.: Google\u2019s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation, arXiv:1609.08144 (2016)"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Li, J., Galley, M., Brockett, C., Gao, J., Dolan, B.: A diversity-promoting objective function for neural conversation models. In: Proceedings of 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 110\u2013119. Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/N16-1014"},{"key":"8_CR27","unstructured":"Zhang, S.,et al.: OPT: Open Pre-trained Transformer Language Models, arxiv:2205.01068 (2022)"},{"key":"8_CR28","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: DeBERTa: Decoding-enhanced BERT with Disentangled Attention, arxiv:2006.03654 (2021)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases: Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43412-9_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T17:46:19Z","timestamp":1703180779000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43412-9_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031434112","9783031434129"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43412-9_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"17 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"In this study, we utilized pretrained LMs for text generation. Pretrained LMs, e.g., GPTs, may contain personal data in the weight parameters. Thus, LMs should be tested in advance and the personal information should be removed from both datasets and models. In this study, we utilized public datasets and models to avoid the misuse of personal information. We confirm that the models did not generate any texts, including any personal information. However, this study can be utilized in deception involving fake documents, news, etc., even though we only intend to improve the quality and diversity of LMs for text generation. Hence, we intend to manage and survey the utilization of this study, to ensure that its negative influences are monitored and constrained.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Statement"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"829","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"196","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.63","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Applied Data Science Track: 239 submissions, 58 accepted papers; Demo Track: 31 submissions, 16 accepted papers.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}