{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:59:30Z","timestamp":1774022370332,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":16,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819681853","type":"print"},{"value":"9789819681860","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-8186-0_20","type":"book-chapter","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T10:17:19Z","timestamp":1750155439000},"page":"247-259","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["TabuLa: Harnessing Language Models for\u00a0Tabular Data Synthesis"],"prefix":"10.1007","author":[{"given":"Zilong","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Robert","family":"Birke","sequence":"additional","affiliation":[]},{"given":"Lydia Y.","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"20_CR1","unstructured":"Avi\u00f1\u00f3, L., Ruffini, M., Gavald\u00e0, R.: Generating synthetic but plausible healthcare record datasets. arXiv preprint arXiv:1807.01514 (2018)"},{"key":"20_CR2","unstructured":"Borisov, V., Sessler, K., Leemann, T., Pawelczyk, M., Kasneci, G.: Language models are realistic tabular data generators. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Kim, J., et al.: SOS: score-based oversampling for tabular data. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022, pp. 762\u2013772. Association for Computing Machinery, New York (2022)","DOI":"10.1145\/3534678.3539454"},{"key":"20_CR4","unstructured":"Kotelnikov, A., Baranchuk, D., Rubachev, I., Babenko, A.: Tabddpm: modelling tabular data with diffusion models. In: International Conference on Machine Learning, pp. 17564\u201317579. PMLR (2023)"},{"key":"20_CR5","first-page":"4263","volume":"34","author":"J Lee","year":"2021","unstructured":"Lee, J., Hyeong, J., Jeon, J., Park, N., Cho, J.: Invertible tabular GANs: killing two birds with one stone for tabular data synthesis. Adv. Neural. Inf. Process. Syst. 34, 4263\u20134273 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR6","unstructured":"Li, J., Zhao, Z., Yee, K., Javaid, U., Sikdar, B.: Taegan: generating synthetic tabular data for data augmentation. arXiv preprint arXiv:2410.01933 (2024)"},{"key":"20_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v074.i11","volume":"74","author":"B Nowok","year":"2016","unstructured":"Nowok, B., Raab, G.M., Dibben, C.: synthpop: bespoke creation of synthetic data in R. J. Stat. Softw. 74, 1\u201326 (2016)","journal-title":"J. Stat. Softw."},{"key":"20_CR8","unstructured":"T.\u00a0S. D.\u00a0V. Project. Copulas (2022)"},{"key":"20_CR9","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)"},{"key":"20_CR10","unstructured":"Solatorio, A.V., Dupriez, O.: Realtabformer: generating realistic relational and tabular data using transformers. arXiv preprint arXiv:2302.02041 (2023)"},{"key":"20_CR11","unstructured":"Xu, L., Skoularidou, M., Cuesta-Infante, A., Veeramachaneni, K.: Modeling tabular data using conditional GAN. In: Advances in Neural Information Processing Systems, vol. 32, pp. 7335\u20137345. Curran Associates, Inc. (2019)"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Zhang, J., Cormode, G., Procopiuc, C.M., Srivastava, D., Xiao, X.: Privbayes: private data release via Bayesian networks. ACM Trans. DataBase Syst. (2017)","DOI":"10.1145\/3134428"},{"key":"20_CR13","unstructured":"Zhao, Z., Kunar, A., Birke, R., Chen, L.Y.: CTAB-GAN: effective table data synthesizing. In: Proceedings of the 13th Asian Conference on Machine Learning, vol. 157, pp. 97\u2013112 (2021)"},{"key":"20_CR14","unstructured":"Zhao, Z., Kunar, A., Birke, R., Chen, L.Y.: CTAB-GAN+: enhancing tabular data synthesis. arXiv preprint arXiv:2204.00401 (2022)"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Aligning books and movies: towards story-like visual explanations by watching movies and reading books. In: The IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.11"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhao, Z., Birke, R., Chen, L.Y.: Permutation-invariant tabular data synthesis. In: 2022 IEEE International Conference on Big Data (Big Data), pp. 5855\u20135864 (2022)","DOI":"10.1109\/BigData55660.2022.10020639"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8186-0_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T10:17:25Z","timestamp":1750155445000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8186-0_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819681853","9789819681860"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8186-0_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"18 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}