{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:40:37Z","timestamp":1758044437880,"version":"3.44.0"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"10","funder":[{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"crossref","award":["2025ZNSFSC1464"],"award-info":[{"award-number":["2025ZNSFSC1464"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"crossref","award":["2024M760357"],"award-info":[{"award-number":["2024M760357"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZB20240115"],"award-info":[{"award-number":["GZB20240115"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2025,10,31]]},"abstract":"<jats:p>\n            Fine-grained Text Style Transfer (FTST) aims to make targeted and precise modifications to specific stylistic components of a sentence. Existing methods typically attempt to disentangle style and content representations for FTST. However, style and content are inherently abstract, making them difficult to formalize and manipulate independently. To address this, we propose a novel framework,\n            <jats:bold>Disentanglement Diffusion Model for Text Style Transfer (DDM4TST)<\/jats:bold>\n            , which reformulates style transformation as either semantic or syntactic transformation. By learning disentangled representations, the model enables accurate and fine-grained style control. Specifically, we construct a feature parsing module to effectively separate semantic and syntactic representations. We then incorporate a diffusion model conditioned on these disentangled representations, allowing for fine-grained control of stylistic attributes while preserving the core content of the original sentence. This integration into the denoising process enhances the controllability and precision of the style transformation. Extensive experiments on the benchmark StylePTB dataset demonstrate that our model consistently outperforms widely adopted baselines. The results validate the effectiveness of our approach in achieving high-quality style transformation while maintaining content fidelity.\n          <\/jats:p>","DOI":"10.1145\/3749195","type":"journal-article","created":{"date-parts":[[2025,7,19]],"date-time":"2025-07-19T11:03:34Z","timestamp":1752923014000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DDM4TST: Diffusion Model for Fine-grained Text Style Transfer by Disentangled Representation"],"prefix":"10.1145","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8162-7071","authenticated-orcid":false,"given":"Cencen","family":"Liu","sequence":"first","affiliation":[{"name":"Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China","place":["Chengdu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6099-9091","authenticated-orcid":false,"given":"Wen","family":"Yin","sequence":"additional","affiliation":[{"name":"Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China","place":["Chengdu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0005-9201","authenticated-orcid":false,"given":"Yi","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China","place":["Chengdu, China"]},{"name":"Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu","place":["Chengdu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9474-0135","authenticated-orcid":false,"given":"Qiugang","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China","place":["Chengdu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4839-0234","authenticated-orcid":false,"given":"Dongyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China","place":["Chengdu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2482-5770","authenticated-orcid":false,"given":"Raza","family":"Ahmad","sequence":"additional","affiliation":[{"name":"Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China","place":["Chengdu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"17981","volume-title":"Advances in Neural Information Processing Systems","author":"Austin Jacob","year":"2021","unstructured":"Jacob Austin, Daniel D. Johnson, Jonathan Ho, Daniel Tarlow, and Rianne van den Berg. 2021. Structured denoising diffusion models in discrete state-spaces. In Advances in Neural Information Processing Systems. M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34, Curran Associates, Inc., 17981\u201317993. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/958c530554f78bcd8e97125b70e6973d-Paper.pdf"},{"key":"e_1_3_1_3_2","first-page":"65","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. Association for Computational Linguistics, Ann Arbor, Michigan, 65\u201372. Retrieved from https:\/\/aclanthology.org\/W05-0909"},{"key":"e_1_3_1_4_2","unstructured":"Haoxing Chen Zhuoer Xu Zhangxuan Gu Jun Lan Xing Zheng Yaohui Li Changhua Meng Huijia Zhu and Weiqiang Wang. 2023. DiffUTE: Universal text editing diffusion model. In Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS\u201923). Curran Associates Inc. Red Hook NY USA 63062\u201363074."},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.673"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1601"},{"key":"e_1_3_1_7_2","volume-title":"Proceedings of the International Conference on Learning Representations, ICLR","author":"Gong Shansan","year":"2023","unstructured":"Shansan Gong, Mukai Li, Jiangtao Feng, Zhiyong Wu, and Lingpeng Kong. 2023. DiffuSeq: Sequence to sequence text generation with diffusion models. In Proceedings of the International Conference on Learning Representations, ICLR."},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.811"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.439"},{"key":"e_1_3_1_10_2","volume-title":"Advances in Neural Information Processing Systems","author":"Hashimoto Tatsunori B.","year":"2018","unstructured":"Tatsunori B. Hashimoto, Kelvin Guu, Yonatan Oren, and Percy S. Liang. 2018. A retrieve-and-edit framework for predicting structured outputs. In Advances in Neural Information Processing Systems. S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.), Vol. 31, Curran Associates, Inc. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2018\/file\/cd17d3ce3b64f227987cd92cd701cc58-Paper.pdf"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.248"},{"key":"e_1_3_1_12_2","first-page":"6840","volume-title":"Advances in Neural Information Processing Systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In Advances in Neural Information Processing Systems. H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33, Curran Associates, Inc., 6840\u20136851. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.781"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544903.3544906"},{"key":"e_1_3_1_15_2","series-title":"Proceedings of Machine Learning Research","first-page":"1587","volume-title":"Proceedings of the 34th International Conference on Machine Learning","volume":"70","author":"Hu Zhiting","year":"2017","unstructured":"Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P. Xing. 2017. Toward controlled generation of text. In Proceedings of the 34th International Conference on Machine Learning. Doina Precup and Yee Whye Teh (Eds.), Proceedings of Machine Learning Research, Vol. 70, PMLR, 1587\u20131596. Retrieved from https:\/\/proceedings.mlr.press\/v70\/hu17e.html"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1306"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1041"},{"key":"e_1_3_1_18_2","first-page":"26302","volume-title":"Advances in Neural Information Processing Systems","author":"Kim Yoon","year":"2021","unstructured":"Yoon Kim. 2021. Sequence-to-sequence learning with latent neural grammars. In Advances in Neural Information Processing Systems. M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34, Curran Associates, Inc., 26302\u201326317. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/dd17e652cd2a08fdb8bf7f68e2ad3814-Paper.pdf"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","unstructured":"Moreno La Quatra Giuseppe Gallipoli and Luca Cagliero. 2024. Self-supervised text style transfer using cycle-consistent adversarial networks. ACM Trans. Intell. Syst. Technol. 15 5 Article 110 (Nov. 2024) 38 pages. 10.1145\/3678179","DOI":"10.1145\/3678179"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1169"},{"key":"e_1_3_1_21_2","first-page":"10820","volume-title":"Advances in Neural Information Processing Systems","author":"Li Jingjing","year":"2020","unstructured":"Jingjing Li, Zichao Li, Lili Mou, Xin Jiang, Michael Lyu, and Irwin King. 2020. Unsupervised text generation by learning from search. In Advances in Neural Information Processing Systems. H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33, Curran Associates, Inc., 10820\u201310831. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/7a677bb4477ae2dd371add568dd19e23-Paper.pdf"},{"key":"e_1_3_1_22_2","first-page":"4328","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Li Xiang","year":"2022","unstructured":"Xiang Li, John Thickstun, Ishaan Gulrajani, Percy S. Liang, and Tatsunori B. Hashimoto. 2022. Diffusion-LM improves controllable text generation. In Advances in Neural Information Processing Systems. S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35, Curran Associates, Inc., 4328\u20134343. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/1be5bc25d50895ee656b8c2d9eb89d6a-Paper-Conference.pdf"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1420"},{"key":"e_1_3_1_24_2","unstructured":"Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out Donia Scott (Ed.). Association for Computational Linguistics Barcelona Spain 74\u201381. https:\/\/aclanthology.org\/W04-1013\/"},{"key":"e_1_3_1_25_2","first-page":"21051","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Lin Zhenghao","year":"2023","unstructured":"Zhenghao Lin, Yeyun Gong, Yelong Shen, Tong Wu, Zhihao Fan, Chen Lin, Nan Duan, and Weizhu Chen. 2023. Text generation with diffusion language models: A pre-training approach with continuous paragraph denoise. In Proceedings of the International Conference on Machine Learning. PMLR, 21051\u201321064."},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3644074"},{"key":"e_1_3_1_27_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Montero Milton Llera","year":"2021","unstructured":"Milton Llera Montero, Casimir J. H. Ludwig, Rui Ponte Costa, Gaurav Malhotra, and Jeffrey S. Bowers. 2021. The role of disentanglement in generalisation. In Proceedings of the International Conference on Learning Representations. OpenReview. Retrieved from https:\/\/iclr.cc\/Conferences\/2025ICLR 2025 : The Thirteenth International Conference on Learning Representations ; Conference date: 24-04-2025 Through 28-04-2025."},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.171"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","unstructured":"Yiwei Lyu Tiange Luo Jiacheng Shi Todd Hollon and Honglak Lee. 2023. Fine-grained text style transfer with diffusion-based language models. In Proceedings of the 8th Workshop on Representation Learning for NLP. Association for Computational Linguistics Toronto Canada 65\u201374. DOI:10.18653\/v1\/2023.repl4nlp-1.6","DOI":"10.18653\/v1\/2023.repl4nlp-1.6"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3665794"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.32"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1012"},{"key":"e_1_3_1_34_2","volume-title":"Advances in Neural Information Processing Systems","author":"Shen Tianxiao","year":"2017","unstructured":"Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi Jaakkola. 2017. Style transfer from non-parallel text by cross-alignment. In Advances in Neural Information Processing Systems. I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30, Curran Associates, Inc. Retrieved fromhttps:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/2d2c8394e31101a261abf1784302bf75-Paper.pdf"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Bashlykov et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv:2307.09288 [cs]. 10.48550\/arXiv.2307.09288","DOI":"10.48550\/arXiv.2307.09288"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6457"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.441"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472621"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21427"},{"key":"e_1_3_1_41_2","unstructured":"Zhirui Zhang Shuo Ren Shujie Liu Jianyong Wang Peng Chen Mu Li Ming Zhou and Enhong Chen. 2018. Style transfer as unsupervised machine translation. ArXiv abs\/1808.07894 (2018). https:\/\/api.semanticscholar.org\/CorpusID:266349854"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.535"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","unstructured":"Hao Zheng and Mirella Lapata. 2023. Real-world compositional generalization with disentangled sequence-to-sequence learning. In Findings of the Association for Computational Linguistics: ACL 2023 Anna Rogers Jordan Boyd-Graber and Naoaki Okazaki (Eds.). Association for Computational Linguistics Toronto Canada 1711\u20131725. 10.18653\/v1\/2023.findings-acl.108","DOI":"10.18653\/v1\/2023.findings-acl.108"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.86"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548239"},{"key":"e_1_3_1_46_2","first-page":"15384","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Zhu Kangchen","year":"2024","unstructured":"Kangchen Zhu, Zhiliang Tian, Jingyu Wei, Ruifeng Luo, Yiping Song, and Xiaoguang Mao. 2024. StyleFlow: Disentangle latent representations via normalizing flow for unsupervised text style transfer. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue (Eds.), ELRA and ICCL, Torino, Italia, 15384\u201315397. Retrieved from https:\/\/aclanthology.org\/2024.lrec-main.1336\/"}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3749195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T12:54:28Z","timestamp":1757681668000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3749195"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"references-count":45,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10,31]]}},"alternative-id":["10.1145\/3749195"],"URL":"https:\/\/doi.org\/10.1145\/3749195","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"type":"print","value":"2375-4699"},{"type":"electronic","value":"2375-4702"}],"subject":[],"published":{"date-parts":[[2025,9,12]]},"assertion":[{"value":"2024-04-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}