{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T15:51:45Z","timestamp":1775663505220,"version":"3.50.1"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1016\/j.knosys.2025.114240","type":"journal-article","created":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T15:49:03Z","timestamp":1754668143000},"page":"114240","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Tapas: enabling faithful data-to-text generation through task-adaptive pre-training with data alignment strategy"],"prefix":"10.1016","volume":"328","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7085-4165","authenticated-orcid":false,"given":"Xin","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoran","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2025.114240_sbref0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2020.106610","article-title":"Neural data-to-text generation with dynamic content planning","volume":"215","author":"Chen","year":"2021","journal-title":"Knowl. Base. Syst."},{"key":"10.1016\/j.knosys.2025.114240_sbref0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112571","article-title":"Enabling controllable table-to-text generation via prompting large language models with guided planning","volume":"304","author":"Zhao","year":"2024","journal-title":"Knowl. Base. Syst."},{"key":"10.1016\/j.knosys.2025.114240_bib0003","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"2023","article-title":"Data-to-text generation with entity modeling","author":"Puduppully","year":"2019"},{"key":"10.1016\/j.knosys.2025.114240_sbref0004","series-title":"Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP","first-page":"91","article-title":"Learning semantic correspondences with less supervision","author":"Liang","year":"2009"},{"key":"10.1016\/j.knosys.2025.114240_bib0005","series-title":"Data Science for Healthcare - Methodologies and Applications","first-page":"147","article-title":"Clinical natural language processing with deep learning","author":"Hasan","year":"2019"},{"key":"10.1016\/j.knosys.2025.114240_bib0006","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"183","article-title":"Few-shot NLG with pre-trained language model","author":"Chen","year":"2020"},{"key":"10.1016\/j.knosys.2025.114240_bib0007","series-title":"Proceedings of the 28th International Conference on Computational Linguistics","first-page":"1978","article-title":"TableGPT: Few-shot table-to-text generation with table structure reconstruction and content matching","author":"Gong","year":"2020"},{"key":"10.1016\/j.knosys.2025.114240_bib0008","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2021","first-page":"910","article-title":"Few-shot table-to-text generation with prototype memory","author":"Su","year":"2021"},{"key":"10.1016\/j.knosys.2025.114240_bib0009","unstructured":"P. Christmann, G. Weikum, Rag-based question answering over heterogeneous data and text, arXiv preprint arXiv:2412.07420(2024)."},{"key":"10.1016\/j.knosys.2025.114240_bib0010","series-title":"Proceedings of the 2019 International Symposium on Signal Processing Systems","first-page":"121","article-title":"Two-level model for table-to-text generation","author":"Cao","year":"2019"},{"key":"10.1016\/j.knosys.2025.114240_bib0011","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"8635","article-title":"KGPT: Knowledge-grounded pre-training for data-to-text generation","author":"Chen","year":"2020"},{"key":"10.1016\/j.knosys.2025.114240_bib0012","series-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","first-page":"2273","article-title":"Structure-aware pre-training for table-to-text generation","author":"Xing","year":"2021"},{"key":"10.1016\/j.knosys.2025.114240_sbref0012","series-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","first-page":"5531","article-title":"PLOG: Table-to-logic pretraining for logical table-to-text generation","author":"Liu","year":"2022"},{"key":"10.1016\/j.knosys.2025.114240_sbref0013","series-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2015"},{"key":"10.1016\/j.knosys.2025.114240_bib0015","series-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"1631","article-title":"Incorporating copying mechanism in sequence-to-sequence learning","author":"Gu","year":"2016"},{"key":"10.1016\/j.knosys.2025.114240_bib0016","series-title":"Proceedings of the 11th International Conference on Natural Language Generation","first-page":"322","article-title":"Findings of the E2E NLG challenge","author":"Du\u0161ek","year":"2018"},{"key":"10.1016\/j.knosys.2025.114240_bib0017","series-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)","first-page":"152","article-title":"A deep ensemble model with slot alignment for sequence-to-sequence natural language generation","author":"Juraska","year":"2018"},{"key":"10.1016\/j.knosys.2025.114240_bib0018","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.1109\/TASLP.2024.3353574","article-title":"TrICy: trigger-guided data-to-text generation with intent aware attention-copy","volume":"32","author":"Agarwal","year":"2024","journal-title":"IEEE ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.knosys.2025.114240_bib0019","first-page":"4881","article-title":"Table-to-text generation by structure-aware seq2seq learning","author":"Liu","year":"2018"},{"key":"10.1016\/j.knosys.2025.114240_bib0020","first-page":"6786","article-title":"Hierarchical encoder with auxiliary supervision for neural table-to-text generation: Learning better representation for tables","author":"Liu","year":"2019"},{"key":"10.1016\/j.knosys.2025.114240_bib0021","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"1072","article-title":"Towards faithful neural table-to-text generation with content-matching constraints","author":"Wang","year":"2020"},{"issue":"17","key":"10.1016\/j.knosys.2025.114240_bib0022","doi-asserted-by":"crossref","first-page":"10339","DOI":"10.1007\/s00521-024-09590-5","article-title":"A novel deep learning model for detection of inconsistency in e-commerce websites","volume":"36","author":"Kassem","year":"2024","journal-title":"Neural Comput. Applic."},{"issue":"1","key":"10.1016\/j.knosys.2025.114240_bib0023","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-024-75549-0","article-title":"A new superfluity deep learning model for detecting knee osteoporosis and osteopenia in x-ray images","volume":"14","author":"Naguib","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.knosys.2025.114240_bib0024","first-page":"1","article-title":"MycGNN: enhancing recommendation diversity in e-commerce through mycelium-inspired graph neural network","author":"Bahi","year":"2024","journal-title":"Electron. Commer. Res."},{"key":"10.1016\/j.knosys.2025.114240_bib0025","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"12824","article-title":"TaPERA: Enhancing faithfulness and interpretability in long-form table QA by content planning and execution-based reasoning","author":"Zhao","year":"2024"},{"key":"10.1016\/j.knosys.2025.114240_bib0026","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2021","first-page":"4106","article-title":"Attend, memorize and generate: Towards faithful table-to-text generation in few shots","author":"Zhao","year":"2021"},{"key":"10.1016\/j.knosys.2025.114240_bib0027","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2021","first-page":"1244","article-title":"TWT: Table with written text for controlled data-to-text generation","author":"Li","year":"2021"},{"key":"10.1016\/j.knosys.2025.114240_sbref0027","series-title":"Proceedings of the 29th International Conference on Computational Linguistics","first-page":"5755","article-title":"GAP: a graph-aware language model framework for knowledge graph-to-text generation","author":"Colas","year":"2022"},{"key":"10.1016\/j.knosys.2025.114240_bib0029","series-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","first-page":"2526","article-title":"JointGT: Graph-text joint representation learning for text generation from knowledge graphs","author":"Ke","year":"2021"},{"key":"10.1016\/j.knosys.2025.114240_bib0030","unstructured":"S. Duwal, S. Prasai, S. Manandhar, Domain-adaptative continual learning for low-resource tasks: Evaluation on Nepali, arXiv preprint arXiv:2412.13860(2024)."},{"key":"10.1016\/j.knosys.2025.114240_bib0031","doi-asserted-by":"crossref","unstructured":"X. Fu, M. Hirano, K. Imajo, Financial fine-tuning a large time series model, arXiv preprint arXiv:2412.09880(2024).","DOI":"10.1109\/CiFer64978.2025.10975735"},{"key":"10.1016\/j.knosys.2025.114240_bib0032","series-title":"Proceedings of the 28th International Conference on Computational Linguistics","first-page":"6838","article-title":"Neural unsupervised domain adaptation in NLP\u2014a survey","author":"Ramponi","year":"2020"},{"key":"10.1016\/j.knosys.2025.114240_bib0033","series-title":"Findings of the Association for Computational Linguistics: ACL 2024","first-page":"10184","article-title":"Efficient continual pre-training for building domain specific large language models","author":"Xie","year":"2024"},{"key":"10.1016\/j.knosys.2025.114240_bib0034","doi-asserted-by":"crossref","unstructured":"A. Cadeddu, A. Chessa, V. De Leo, G. Fenu, E. Motta, F. Osborne, D.R. Recupero, A. Salatino, L. Secchi, A comparative study of task adaptation techniques of large language models for identifying sustainable development goals, arXiv preprint arXiv:2506.15208(2025).","DOI":"10.1109\/ACCESS.2025.3618017"},{"key":"10.1016\/j.knosys.2025.114240_bib0035","doi-asserted-by":"crossref","unstructured":"W. Zhai, H. Qi, Q. Zhao, J. Li, Z. Wang, H. Wang, B.X. Yang, G. Fu, Chinese mentalBERT: Domain-adaptive pre-training on social media for Chinese mental health text analysis, arXiv preprint arXiv:2402.09151(2024).","DOI":"10.18653\/v1\/2024.findings-acl.629"},{"key":"10.1016\/j.knosys.2025.114240_bib0036","series-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"1337","article-title":"Structure-grounded pretraining for text-to-SQL","author":"Deng","year":"2021"},{"key":"10.1016\/j.knosys.2025.114240_bib0037","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4060","article-title":"Pragmatically informative text generation","author":"Shen","year":"2019"},{"key":"10.1016\/j.knosys.2025.114240_bib0038","doi-asserted-by":"crossref","unstructured":"H. Ta, Self-training from self-memory in data-to-text generation, CoRR(2024). arXiv:abs\/2401.1056710.48550\/ARXIV.2401.10567.","DOI":"10.2139\/ssrn.4719908"},{"key":"10.1016\/j.knosys.2025.114240_bib0039","series-title":"Proceedings of the 11th International Conference on Natural Language Generation","first-page":"360","article-title":"Handling rare items in data-to-text generation","author":"Shimorina","year":"2018"},{"key":"10.1016\/j.knosys.2025.114240_bib0040","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1173","article-title":"ToTTo: A controlled table-to-text generation dataset","author":"Parikh","year":"2020"},{"key":"10.1016\/j.knosys.2025.114240_bib0041","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","first-page":"185","article-title":"A partition filter network for joint entity and relation extraction","author":"Yan","year":"2021"},{"key":"10.1016\/j.knosys.2025.114240_bib0042","series-title":"Soviet physics Doklady","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume":"volume 10","author":"Levenshtein","year":"1966"},{"key":"10.1016\/j.knosys.2025.114240_bib0043","series-title":"Proceedings of the 10th International Conference on Natural Language Generation","first-page":"124","article-title":"The WebNLG challenge: Generating text from RDF data","author":"Gardent","year":"2017"},{"key":"10.1016\/j.knosys.2025.114240_bib0044","series-title":"The Semantic Web, 6th International Semantic Web Conference, 2nd Asian Semantic Web Conference, ISWC 2007 + ASWC 2007, Busan, Korea, November 11\u201315, 2007","first-page":"722","article-title":"Dbpedia: a nucleus for a web of open data","volume":"volume 4825","author":"Auer","year":"2007"},{"key":"10.1016\/j.knosys.2025.114240_sbref0039","series-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2015"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512501281X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512501281X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T15:51:18Z","timestamp":1762271478000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095070512501281X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":45,"alternative-id":["S095070512501281X"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2025.114240","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2025,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Tapas: enabling faithful data-to-text generation through task-adaptive pre-training with data alignment strategy","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2025.114240","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114240"}}