{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:23:09Z","timestamp":1764994989537,"version":"3.46.0"},"reference-count":44,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2025,12,1]]},"DOI":"10.1587\/transfun.2025eap1042","type":"journal-article","created":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T18:07:13Z","timestamp":1750010833000},"page":"1687-1697","source":"Crossref","is-referenced-by-count":0,"title":["Diversify Question Generation Based on Diffusion Model in Dialogue"],"prefix":"10.1587","volume":"E108.A","author":[{"given":"Fan","family":"XU","sequence":"first","affiliation":[{"name":"School of Computer Information Engineering, Jiangxi Prov. Key Lab. for HPC, the State Int\u2019l S&T Coop. Base of Net. Support. Softw., Jiangxi Normal University"},{"name":"Language Intelligence Res. Center, Jiangxi Normal University"}]},{"given":"Sumin","family":"LIU","sequence":"additional","affiliation":[{"name":"School of Computer Information Engineering, Jiangxi Normal University"}]},{"given":"Keyu","family":"YAN","sequence":"additional","affiliation":[{"name":"School of Computer Information Engineering, Jiangxi Prov. Key Lab. for HPC, the State Int\u2019l S&T Coop. Base of Net. Support. Softw., Jiangxi Normal University"}]},{"given":"Baishun","family":"LI","sequence":"additional","affiliation":[{"name":"Jinxi County No.1 Middle School"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] V. Rus, B. Wyse, P. Piwek, M. Lintean, S. Stoyanchev, and C. Moldovan, \u201cA detailed account of the first question generation shared task evaluation challenge,\u201d Dialogue and Discourse, vol.3, no.2, pp.177-204, 2012. 10.5087\/dad.2012.208","DOI":"10.5087\/dad.2012.208"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] N. Mulla and P. Gharpure, \u201cAutomatic question generation: A review of methodologies, datasets, evaluation metrics, and applications,\u201d Progress in Artificial Intelligence, vol.12, pp.1-32, 2023. 10.1007\/s13748-023-00295-9","DOI":"10.1007\/s13748-023-00295-9"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] G. Kurdi, J. Leo, B. Parsia, U. Sattler, and S. Al-Emari, \u201cA systematic review of automatic question generation for educational purposes,\u201d Int. J. Artif. Intell. Educ., vol.30, pp.121-204, 2020. 10.1007\/s40593-019-00186-y","DOI":"10.1007\/s40593-019-00186-y"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] X. Sun, J. Liu, Y. Lyu, W. He, Y. Ma, and S. Wang, \u201cAnswer-focused and position-aware neural question generation,\u201d Proc. Conference on Empirical Methods in Natural Language Processing, pp.3930-3939, 2018. 10.18653\/v1\/d18-1427","DOI":"10.18653\/v1\/D18-1427"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] Y. Kim, H. Lee, J. Shin, and K. Jung, \u201cImproving neural question generation using answer separation,\u201d Proc. Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, pp.6602-6609, 2019. 10.1609\/aaai.v33i01.33016602","DOI":"10.1609\/aaai.v33i01.33016602"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] J. Li, Y. Gao, L. Bing, I. King, and M.R. Lyu, \u201cImproving question generation with to the point context,\u201d Proc. 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp.3216-3226, 2019. 10.18653\/v1\/d19-1317","DOI":"10.18653\/v1\/D19-1317"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] X. Jia, W. Zhou, X. Sun, and Y. Wu, \u201cHow to ask good questions? Try to leverage paraphrases,\u201d Proc. 58th Annual Meeting of the Association for Computational Linguistics, pp.6130-6140, 2020. 10.18653\/v1\/2020.acl-main.545","DOI":"10.18653\/v1\/2020.acl-main.545"},{"key":"8","unstructured":"[8] Y. Chen, L. Wu, and M.J. Zaki, \u201cNatural question generation with reinforcement learning based graph-to-sequence model,\u201d Proc. 33rd Conference on Neural Information Processing Systems, pp.1-10, 2019."},{"key":"9","unstructured":"[9] J. Ho, A. Jain, and P. Abbeel, \u201cDenoising diffusion probabilistic models,\u201d Advances in Neural Information Processing Systems, vol.33, pp.6840-6851, 2020."},{"key":"10","unstructured":"[10] T. Wu, Z. Fan, X. Liu, et al., \u201cAr-diffusion: Auto-regressive diffusion model for text generation,\u201d Proc. Advances in Neural Information Processing Systems, vol.36, pp.39957-39974, 2023."},{"key":"11","unstructured":"[11] M. Heilman and N.A. Smith, \u201cGood question! statistical ranking for question generation,\u201d Proc. Human Language Technologies: the Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp.609-617, 2010."},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] Y. Chali and S.A. Hasan, \u201cTowards topic-to-question generation,\u201d Computational Linguistics, vol.41, no.1, pp.1-20, 2015. 10.1162\/coli_a_00206","DOI":"10.1162\/COLI_a_00206"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] X. Du, J. Shao, and C. Cardie, \u201cLearning to ask: Neural question generation for reading comprehension,\u201d Proc. 55th Annual Meeting of the Association for Computational Linguistics, pp.1342-1352, 2017. 10.18653\/v1\/p17-1123","DOI":"10.18653\/v1\/P17-1123"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] Q. Zhou, N. Yang, F. Wei, C. Tan, H. Bao, and M. Zhou, \u201cNeural question generation from text: A preliminary study,\u201d Natural Language Processing and Chinese Computing, Lecture Notes in Computer Science, vol.10619, pp.662-671, 2018. 10.1007\/978-3-319-73618-1_56","DOI":"10.1007\/978-3-319-73618-1_56"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] L. Song, Z. Wang, W. Hamza, Y. Zhang, and D. Gildea, \u201cLeveraging context information for natural question generation,\u201d Proc. 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp.569-574, 2018. 10.18653\/v1\/n18-2090","DOI":"10.18653\/v1\/N18-2090"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] B. Liu, M. Zhao, D. Niu, K. Lai, Y. He, H. Wei, and Y. Xu, \u201cLearning to generate questions by learning what not to generate,\u201d Proc. World Wide Web Conference, pp.1106-1118, 2019. 10.1145\/3308558.3313737","DOI":"10.1145\/3308558.3313737"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] W. Zhou, M. Zhang, and Y. Wu, \u201cMulti-task learning with language modeling for question generation,\u201d Proc. Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp.3394-3399, 2019. 10.18653\/v1\/d19-1337","DOI":"10.18653\/v1\/D19-1337"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] S. Bao, H. He, F. Wang, H. Wu, and H. Wang, \u201cPLATO: Pre-trained dialogue generation model with discrete latent variable,\u201d Proc. 58th Annual Meeting of the Association for Computational Linguistics, pp.85-96, 2020. 10.18653\/v1\/2020.acl-main.9","DOI":"10.18653\/v1\/2020.acl-main.9"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] B. Sun, S. Feng, Y. Li, J. Liu, and K. Li, \u201cGenerating relevant and coherent dialogue responses using self-separated conditional variational AutoEncoders,\u201d Proc. 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pp.5624-5637, 2021. 10.18653\/v1\/2021.acl-long.437","DOI":"10.18653\/v1\/2021.acl-long.437"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] W. Chen, Y. Gong, S. Wang, B. Yao, W. Qi, Z. Wei, X. Hu, B. Zhou, Y. Mao, W. Chen, B. Cheng, and N. Duan, \u201cDialogVED: A pre-trained latent variable encoder-decoder model for dialog response generation,\u201d Proc. 60th Annual Meeting of the Association for Computational Linguistics, pp.4852-4864, 2022. 10.18653\/v1\/2022.acl-long.333","DOI":"10.18653\/v1\/2022.acl-long.333"},{"key":"21","unstructured":"[21] P. Dhariwal and A. Nichol, \u201cDiffusion models beat GANs on image synthesis,\u201d Proc. 35th International Conference on Neural Information Processing Systems, pp.8780-8794, 2021."},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] G. Liu, Z. Feng, Y. Gao, Z. Yang, X. Liang, J. Bao, X. He, S. Cui, Z. Li, and Z. Hu, \u201cComposable text controls in latent space with ODEs,\u201d Proc. Conference on Empirical Methods in Natural Language Processing, pp.16543-16570, 2023. 10.18653\/v1\/2023.emnlp-main.1030","DOI":"10.18653\/v1\/2023.emnlp-main.1030"},{"key":"23","doi-asserted-by":"publisher","unstructured":"[23] Yujie Wei and Kui Jin, \u201cConditional question generation model based on diffusion model,\u201d Proc. Advances in Computer, Signals and Systems, pp.37-42, 2024. 10.23977\/acss.2024.080705","DOI":"10.23977\/acss.2024.080705"},{"key":"24","unstructured":"[24] J. Song, C. Meng, and S. Ermon, \u201cDenoising diffusion implicit models,\u201d Proc. ICLR, pp.1-22, 2021."},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] Y. Peng, Y. Bao, Y. Chen, C. Wu, and C. Guo, \u201cOptimus: An efficient dynamic resource scheduler for deep learning clusters,\u201d Proc. Thirteenth EuroSys Conference, pp.1-14, 2018. 10.1145\/3190508.3190517","DOI":"10.1145\/3190508.3190517"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] T. Zhao, R. Zhao, and M. Eskenazi, \u201cLearning discourse-level diversity for neural dialog models using conditional variational autoencoders,\u201d Proc. 55th Annual Meeting of the Association for Computational Linguistics, pp.654-664, 2017. 10.18653\/v1\/p17-1061","DOI":"10.18653\/v1\/P17-1061"},{"key":"27","doi-asserted-by":"publisher","unstructured":"[27] C. Meister, T. Vieira, and R. Cotterell, \u201cBest-first beam search,\u201d Trans. Association for Computational Linguistics, vol.8, pp.795-809, 2020. 10.1162\/tacl_a_00346","DOI":"10.1162\/tacl_a_00346"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] Y. Xu, D. Wang, M. Yu, D. Ritchie, B. Yao, T. Wu, Z. Zhang, T. Li, N. Bradford, B. Sun, T. Hoang, Y. Sang, Y. Hou, X. Ma, D. Yang, N. Peng, Z. Yu, and M. Warschauer, \u201cFantastic questions and where to find them: FairytaleQA\u2006\u2014\u2006An authentic dataset for narrative comprehension,\u201d Proc. 60th Annual Meeting of the Association for Computational Linguistics, pp.447-460, 2022. 10.18653\/v1\/2022.acl-long.34","DOI":"10.18653\/v1\/2022.acl-long.34"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] Y.K. Lal, N. Chambers, R. Mooney, and N. Balasubramanian, \u201cTellMeWhy: A dataset for answering why-questions in narratives,\u201d Findings of the Association for Computational Linguistics: ACL-IJCNLP, pp.596-610, 2021. 10.18653\/v1\/2021.findings-acl.53","DOI":"10.18653\/v1\/2021.findings-acl.53"},{"key":"30","unstructured":"[30] I. Loshchilov and F. Hutter, \u201cDecoupled weight decay regularization,\u201d Proc. ICLR, pp.1-18, 2019."},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu, \u201cBLEU: A method for automatic evaluation of machine translation,\u201d Proc. 40th Annual Meeting of the Association for Computational Linguistics, pp.311-318, 2002. 10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"32","unstructured":"[32] C.-Y. Lin, \u201cRouge: A package for automatic evaluation of summaries,\u201d Proc. Text Summarization Branches Out, pp.74-81, 2004."},{"key":"33","unstructured":"[33] T. Zhang, V. Kishore, F. Wu, K.Q. Weinberger, and Y. Artzi, \u201cBERTScore: Evaluating text generation with BERT,\u201d Proc. ICLR, pp.1-43, 2020."},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] S. Eo, H. Moon, J. Kim, Y. Hur, J. Kim, S. Lee, C. Chun, S. Park, and H. Lim, \u201cTowards diverse and effective question-answer pair generation from children storybooks,\u201d Findings of the Association for Computational Linguistics: ACL, pp.6100-6115, 2023. 10.18653\/v1\/2023.findings-acl.380","DOI":"10.18653\/v1\/2023.findings-acl.380"},{"key":"35","doi-asserted-by":"crossref","unstructured":"[35] H. Yoon and J. Bak, \u201cDiversity enhanced narrative question generation for storybooks,\u201d Proc. Conference on Empirical Methods in Natural Language Processing, pp.465-482, 2023. 10.18653\/v1\/2023.emnlp-main.31","DOI":"10.18653\/v1\/2023.emnlp-main.31"},{"key":"36","doi-asserted-by":"crossref","unstructured":"[36] S. Gong, M. Li, J. Feng, Z. Wu, and L. Kong, \u201cDiffuSeq-v2: Bridging discrete and continuous text spaces for accelerated seq2seq diffusion models,\u201d Findings of the Association for Computational Linguistics: EMNLP, pp.9868-9875, 2023. 10.18653\/v1\/2023.findings-emnlp.660","DOI":"10.18653\/v1\/2023.findings-emnlp.660"},{"key":"37","doi-asserted-by":"crossref","unstructured":"[37] H. Yuan, Z. Yuan, C. Tan, F. Huang, and S. Huang, \u201cText diffusion model with encoder-decoder transformers for sequence-to-sequence generation,\u201d Proc. Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp.22-39, 2024. 10.18653\/v1\/2024.naacl-long.2","DOI":"10.18653\/v1\/2024.naacl-long.2"},{"key":"38","unstructured":"[38] A. Liu, B. Feng, B. Wang, et al., \u201cDeepseek-v2: A strong, economical, and efficient mixture-of-experts language model,\u201d arXiv preprint, arXiv:2405.04434, 2024. 10.48550\/arXiv.2405.04434"},{"key":"39","unstructured":"[39] A. Grattafiori, A. Dubey, A. Jauhri, et al., \u201cThe llama 3 herd of models,\u201d arXiv preprint, arXiv:2407.21783, 2024. 10.48550\/arXiv.2407.21783"},{"key":"40","doi-asserted-by":"crossref","unstructured":"[40] P. Rajpurkar, J. Zhang, K. Lopyrev, and P. Liang, \u201cSQuAD: 100,000+ questions for machine comprehension of text,\u201d Proc. Conference on Empirical Methods in Natural Language Processing, pp.2383-2392, 2016. 10.18653\/v1\/d16-1264","DOI":"10.18653\/v1\/D16-1264"},{"key":"41","doi-asserted-by":"crossref","unstructured":"[41] P. Rajpurkar, R. Jia, and P. Liang, \u201cKnow what you don\u2019t know: Unanswerable questions for SQuAD,\u201d Proc. 56th Annual Meeting of the Association for Computational Linguistics, pp.784-789, 2018. 10.18653\/v1\/p18-2124","DOI":"10.18653\/v1\/P18-2124"},{"key":"42","doi-asserted-by":"crossref","unstructured":"[42] K. Chu, Y.-P. Chen, and H. Nakayama, \u201cExploring and controlling diversity in LLM-agent conversation,\u201d arXiv preprint, arXiv:2412.21102v2, 2025. 10.48550\/arXiv.2412.21102","DOI":"10.18653\/v1\/2025.findings-emnlp.1397"},{"key":"43","doi-asserted-by":"crossref","unstructured":"[43] W. Wang, H. Bao, S. Huang, L. Dong, and F. Wei, \u201cMiniLMv2: Multi-head self-attention relation distillation for compressing pretrained transformers,\u201d Findings of the Association for Computational Linguistics: ACL-IJCNLP, pp.2140-2151, 2021. 10.18653\/v1\/2021.findings-acl.188","DOI":"10.18653\/v1\/2021.findings-acl.188"},{"key":"44","doi-asserted-by":"crossref","unstructured":"[44] N. Reimers and I. Gurevych, \u201cSentence-BERT: Sentence embeddings using siamese BERT-networks,\u201d Proc. 2019 Conference on Empirical Methods in Natural Language. Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp.3982-3992, 2019. 10.18653\/v1\/d19-1410","DOI":"10.18653\/v1\/D19-1410"}],"container-title":["IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E108.A\/12\/E108.A_2025EAP1042\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T03:24:58Z","timestamp":1764991498000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E108.A\/12\/E108.A_2025EAP1042\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":44,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2025eap1042","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"type":"print","value":"0916-8508"},{"type":"electronic","value":"1745-1337"}],"subject":[],"published":{"date-parts":[[2025,12,1]]},"article-number":"2025EAP1042"}}