{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:56:03Z","timestamp":1787018163305,"version":"build-2736575974"},"reference-count":66,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T00:00:00Z","timestamp":1709856000000},"content-version":"vor","delay-in-days":67,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Data-to-text (D2T) generation aims to transform structured data into natural language text. Data-to-text pre-training has proved to be powerful in enhancing D2T generation and yields impressive performance. However, previous pre-training methods either oversimplified structured data into a sequence without considering input structures or designed training objectives tailored for a specific data structure (e.g., table or knowledge graph). In this paper, we unify different types of structured data (i.e., table, key-value data, knowledge graph) into the graph format and cast different D2T generation tasks as graph-to-text generation. To effectively exploit the structural information of the input graph, we propose a structure-enhanced pre-training method for D2T generation by designing a structure-enhanced Transformer. Concretely, we devise a position matrix for the Transformer, encoding relative positional information of connected nodes in the input graph. In addition, we propose a new attention matrix to incorporate graph structures into the original Transformer by taking the available explicit connectivity structure into account. Extensive experiments on six benchmark datasets show the effectiveness of our model. Our source codes are available at https:\/\/github.com\/AlibabaResearch\/DAMO-ConvAI\/tree\/main\/unid2t.<\/jats:p>","DOI":"10.1162\/tacl_a_00641","type":"journal-article","created":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T15:55:50Z","timestamp":1709913350000},"page":"210-228","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":16,"title":["Unifying Structured Data as Graph for Data-to-Text\n                    Pre-Training"],"prefix":"10.1162","volume":"12","author":[{"given":"Shujie","family":"Li","sequence":"first","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China. sj.li1@siat.ac.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiying","family":"Geng","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China. min.yang@siat.ac.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binhua","family":"Li","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanghu","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanwei","family":"He","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shao","family":"Yuan","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Can","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Huang","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongbin","family":"Li","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, China. shuide.lyb@alibaba-inc.com"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2024,3,8]]},"reference":[{"key":"2024030820554200400_bib1","doi-asserted-by":"publisher","first-page":"3554","DOI":"10.18653\/v1\/2021.naacl-main.278","article-title":"Knowledge graph based synthetic corpus\n                        generation for knowledge-enhanced language model\n                        pre-training","volume-title":"Proceedings of the 2021 Conference\n                        of the North American Chapter of the Association for Computational\n                        Linguistics: Human Language Technologies","author":"Agarwal","year":"2021"},{"key":"2024030820554200400_bib2","article-title":"Cont: Contrastive neural text\n                        generation","author":"An","year":"2022","journal-title":"arXiv preprint\n                    arXiv:2205.14690"},{"key":"2024030820554200400_bib3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.503","article-title":"Table-to-text generation and pre-training with\n                        tabt5","author":"Andrejczuk","year":"2022","journal-title":"arXiv preprint arXiv:2210.09162"},{"key":"2024030820554200400_bib4","doi-asserted-by":"crossref","first-page":"6001","DOI":"10.18653\/v1\/2022.acl-long.415","article-title":"Graph pre-training for amr parsing and\n                        generation","volume-title":"Proceedings of the 60th Annual\n                        Meeting of the Association for Computational Linguistics (Volume 1: Long\n                        Papers)","author":"Bai","year":"2022"},{"key":"2024030820554200400_bib5","first-page":"65","article-title":"Meteor: An automatic metric for MT evaluation\n                        with improved correlation with human judgments","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic\n                        Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee","year":"2005"},{"key":"2024030820554200400_bib6","doi-asserted-by":"publisher","first-page":"8681","DOI":"10.18653\/v1\/2020.emnlp-main.700","article-title":"Palm: Pre-training an autoencoding&autoregressive\n                        language model for context-conditioned generation","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural\n                        Language Processing (EMNLP)","author":"Bi","year":"2020"},{"key":"2024030820554200400_bib7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6243","article-title":"Graph transformer for graph-to-sequence\n                        learning","volume-title":"AAAI","author":"Cai","year":"2020"},{"key":"2024030820554200400_bib8","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1145\/1390156.1390173","article-title":"Learning to sportscast: A test of grounded\n                        language acquisition","volume-title":"Proceedings of the 25th\n                        International Conference on Machine Learning","author":"Chen","year":"2008"},{"key":"2024030820554200400_bib9","doi-asserted-by":"publisher","first-page":"193","DOI":"10.18653\/v1\/2021.findings-acl.17","article-title":"Wikitablet: A large-scale data-to-text\n                        dataset for generating Wikipedia article sections","volume-title":"Findings of the Association for Computational Linguistics:\n                        ACL-IJCNLP 2021","author":"Chen","year":"2021"},{"key":"2024030820554200400_bib10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.708","article-title":"Logical natural language generation from\n                        open-domain tables","author":"Chen","year":"2020","journal-title":"arXiv preprint\n                        arXiv:2004.10404"},{"key":"2024030820554200400_bib11","doi-asserted-by":"publisher","first-page":"8635","DOI":"10.18653\/v1\/2020.emnlp-main.697","article-title":"Kgpt: Knowledge-grounded pre-training for\n                        data-to-text generation","volume-title":"Proceedings of the 2020\n                        Conference on Empirical Methods in Natural Language Processing\n                        (EMNLP)","author":"Chen","year":"2020"},{"key":"2024030820554200400_bib12","article-title":"Control prefixes for text generation","author":"Clive","year":"2021","journal-title":"arXiv preprint arXiv:2110.08329"},{"key":"2024030820554200400_bib13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1483","article-title":"Handling divergent reference texts when\n                        evaluating table-to-text generation","volume-title":"ACL","author":"Dhingra","year":"2019"},{"key":"2024030820554200400_bib14","first-page":"13042","article-title":"Unified language model pre-training for natural language\n                        understanding and generation","volume-title":"Advances in Neural\n                        Information Processing Systems 32: Annual Conference on Neural Information\n                        Processing Systems 2019, NeurIPS 2019, December 8\u201314, 2019,\n                        Vancouver, BC, Canada","author":"Li","year":"2019"},{"key":"2024030820554200400_bib15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2008","article-title":"Sequence-to-sequence generation for spoken\n                        dialogue via deep syntax trees and strings","author":"Du\u0161ek","year":"2016","journal-title":"arXiv\n                        preprint arXiv:1606.05491"},{"key":"2024030820554200400_bib16","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.csl.2019.06.009","article-title":"Evaluating the state-of-the-art of\n                        end-to-end natural language generation: The E2E NLG\n                        challenge","volume":"59","author":"Du\u0161ek","year":"2020","journal-title":"Computer Speech &\n                        Language"},{"key":"2024030820554200400_bib17","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/978-3-031-00129-1_13","article-title":"A faithful contrastive framework for response\n                        generation in tableqa systems","volume-title":"International\n                        Conference on Database Systems for Advanced Applications","author":"Fang","year":"2022"},{"key":"2024030820554200400_bib18","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/978-3-031-00129-1_13","article-title":"Falcon: A faithful contrastive framework for\n                        response generation in tableqa systems","volume-title":"International Conference on Database Systems for Advanced\n                        Applications","author":"Fang","year":"2022"},{"key":"2024030820554200400_bib19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1017","article-title":"Creating training corpora for nlg\n                        micro-planning","volume-title":"55th Annual Meeting of the\n                        Association for Computational Linguistics (ACL)","author":"Gardent","year":"2017"},{"key":"2024030820554200400_bib20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00269","article-title":"Densely connected graph convolutional\n                        networks for graph-to-sequence learning","volume":"7","author":"Guo","year":"2019","journal-title":"Transactions of the Association for Computational\n                        Linguistics"},{"key":"2024030820554200400_bib21","doi-asserted-by":"publisher","first-page":"4845","DOI":"10.18653\/v1\/2022.emnlp-main.321","article-title":"Self-supervised graph masking pre-training\n                        for graph-to-text generation","volume-title":"Empirical Methods\n                        in Natural Language Processing 2022","author":"Han","year":"2022"},{"key":"2024030820554200400_bib22","doi-asserted-by":"publisher","first-page":"4320","DOI":"10.18653\/v1\/2020.acl-main.398","article-title":"Tapas: Weakly supervised table parsing via\n                        pre-training","volume-title":"Proceedings of the 58th Annual\n                        Meeting of the Association for Computational Linguistics","author":"Herzig","year":"2020"},{"key":"2024030820554200400_bib23","doi-asserted-by":"publisher","first-page":"97","DOI":"10.18653\/v1\/2020.inlg-1.14","article-title":"Text-to-text pre-training for data-to-text\n                        tasks","volume-title":"Proceedings of the 13th International\n                        Conference on Natural Language Generation","author":"Kale","year":"2020"},{"key":"2024030820554200400_bib24","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.18653\/v1\/2021.findings-acl.223","article-title":"Jointgt: Graph-text joint representation\n                        learning for text generation from knowledge graphs","volume-title":"Findings of the Association for Computational Linguistics:\n                        ACL-IJCNLP 2021","author":"Ke","year":"2021"},{"key":"2024030820554200400_bib25","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional\n                        transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Devlin","year":"2019"},{"key":"2024030820554200400_bib26","first-page":"2284","article-title":"Text generation from knowledge graphs with\n                        graph transformers","volume-title":"Proceedings of the 2019\n                        Conference of the North American Chapter of the Association for\n                        Computational Linguistics: Human Language Technologies, Volume 1 (Long and\n                        Short Papers)","author":"Koncel-Kedziorski","year":"2019"},{"key":"2024030820554200400_bib27","article-title":"Albert: A lite bert for self-supervised\n                        learning of language representations","volume-title":"International Conference on Learning\n                    Representations","author":"Lan","year":"2019"},{"key":"2024030820554200400_bib28","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.18653\/v1\/D16-1128","article-title":"Neural text generation from structured data with application\n                        to the biography domain","volume-title":"Proceedings of the 2016\n                        Conference on Empirical Methods in Natural Language Processing","author":"Lebret","year":"2016"},{"key":"2024030820554200400_bib29","first-page":"110","article-title":"A diversity-promoting objective function for\n                        neural conversation models","volume-title":"NAACL HLT 2016, The\n                        2016 Conference of the North American Chapter of the Association for\n                        Computational Linguistics: Human Language Technologies, San Diego\n                        California, USA, June 12\u201317, 2016","author":"Li","year":"2016"},{"key":"2024030820554200400_bib30","doi-asserted-by":"publisher","first-page":"2983","DOI":"10.18653\/v1\/2023.acl-long.168","article-title":"CATS: A pragmatic Chinese answer-to-sequence dataset with\n                        large scale and high quality","volume-title":"Proceedings of the\n                        61st Annual Meeting of the Association for Computational Linguistics (Volume\n                        1: Long Papers)","author":"Li","year":"2023"},{"key":"2024030820554200400_bib31","article-title":"Cats: A pragmatic chinese answer-to-sequence dataset with\n                        large scale and high quality","author":"Li","year":"2023","journal-title":"arXiv preprint\n                        arXiv:2306.11477"},{"key":"2024030820554200400_bib32","first-page":"6115","article-title":"Graph-to-text generation with dynamic structure\n                        pruning","volume-title":"Proceedings of the 29th International\n                        Conference on Computational Linguistics","author":"Li","year":"2022"},{"key":"2024030820554200400_bib33","doi-asserted-by":"publisher","first-page":"91","DOI":"10.3115\/1687878.1687893","article-title":"Learning semantic correspondences with less\n                        supervision","volume-title":"Proceedings of the Joint Conference\n                        of the 47th Annual Meeting of the ACL and the 4th International Joint\n                        Conference on Natural Language Processing of the AFNLP","author":"Liang","year":"2009"},{"key":"2024030820554200400_bib34","first-page":"74","article-title":"Rouge: A package for automatic evaluation of\n                        summaries","volume-title":"Text Summarization Branches\n                        Out","author":"Lin","year":"2004"},{"key":"2024030820554200400_bib35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.373","article-title":"Plog: Table-to-logic pretraining for logical\n                        table-to-text generation","author":"Ao","year":"2022","journal-title":"arXiv preprint\n                        arXiv:2205.12697"},{"key":"2024030820554200400_bib36","doi-asserted-by":"publisher","first-page":"4881","DOI":"10.1609\/aaai.v32i1.11925","article-title":"Table-to-text generation by structure-aware seq2seq\n                        learning","volume-title":"Proceedings of the Thirty-Second AAAI\n                        Conference on Artificial Intelligence, (AAAI-18), the 30th innovative\n                        Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI\n                        Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New\n                        Orleans, Louisiana, USA, February 2\u20137, 2018","author":"Liu","year":"2018"},{"key":"2024030820554200400_bib37","doi-asserted-by":"crossref","first-page":"4205","DOI":"10.18653\/v1\/2022.acl-long.289","article-title":"Improving compositional generalization\n                        with self-training for data-to-text generation","volume-title":"Proceedings of the 60th Annual Meeting of the Association for\n                        Computational Linguistics (Volume 1: Long Papers)","author":"Mehta","year":"2022"},{"key":"2024030820554200400_bib38","article-title":"Dart: Open-domain structured data record\n                        to text generation","author":"Nan","year":"2020","journal-title":"arXiv preprint\n                        arXiv:2007.02871"},{"key":"2024030820554200400_bib39","doi-asserted-by":"publisher","first-page":"2223","DOI":"10.18653\/v1\/2020.findings-emnlp.202","article-title":"Reinforcement learning with imbalanced\n                        dataset for data-to-text medical report generation","volume-title":"Findings of the Association for Computational Linguistics: EMNLP\n                        2020","author":"Nishino","year":"2020"},{"key":"2024030820554200400_bib40","doi-asserted-by":"publisher","first-page":"311","DOI":"10.3115\/1073083.1073135","article-title":"BLEU: A method for automatic evaluation of machine\n                        translation","volume-title":"Proceedings of the 40th Annual\n                        Meeting of the Association for Computational Linguistics","author":"Papineni","year":"2002"},{"key":"2024030820554200400_bib41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.89","article-title":"Totto: A controlled table-to-text generation\n                        dataset","author":"Parikh","year":"2020","journal-title":"arXiv preprint arXiv:2004.14373"},{"key":"2024030820554200400_bib42","doi-asserted-by":"publisher","first-page":"10","DOI":"10.18653\/v1\/2021.textgraphs-1.2","article-title":"Modeling graph structure via relative\n                        position for text generation from knowledge graphs","author":"Schmitt","year":"2021","journal-title":"NAACL-HLT 2021"},{"key":"2024030820554200400_bib43","doi-asserted-by":"publisher","first-page":"392","DOI":"10.18653\/v1\/W15-3049","article-title":"chrf: character n-gram f-score for\n                        automatic mt evaluation","volume-title":"Proceedings of the Tenth\n                        Workshop on Statistical Machine Translation","author":"Popovi\u0107","year":"2015"},{"key":"2024030820554200400_bib44","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1162\/tacl_a_00484","article-title":"Data-to-text generation with variational\n                        sequential planning","volume":"10","author":"Puduppully","year":"2022","journal-title":"Transactions of the Association\n                        for Computational Linguistics"},{"key":"2024030820554200400_bib45","volume-title":"Improving Language Understanding by Generative\n                        Pre-Training","author":"Radford","year":"2018"},{"issue":"140","key":"2024030820554200400_bib46","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified\n                        text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine\n                        Learning Research"},{"key":"2024030820554200400_bib47","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/978-3-030-45439-5_5","article-title":"A hierarchical model for data-to-text\n                        generation","volume-title":"European Conference on Information\n                        Retrieval","author":"Rebuffel","year":"2020"},{"issue":"1","key":"2024030820554200400_bib48","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1017\/S1351324997001502","article-title":"Building applied natural language generation\n                        systems","volume":"3","author":"Reiter","year":"1997","journal-title":"Natural Language Engineering"},{"key":"2024030820554200400_bib49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.nlp4convai-1.20","article-title":"Investigating pretrained language models\n                        for graph-to-text generation","author":"Ribeiro","year":"2020","journal-title":"arXiv preprint\n                        arXiv:2007 .08426"},{"key":"2024030820554200400_bib50","doi-asserted-by":"publisher","first-page":"211","DOI":"10.18653\/v1\/2021.nlp4convai-1.20","article-title":"Investigating pretrained language models\n                        for graph-to-text generation","volume-title":"Proceedings of the\n                        3rd Workshop on Natural Language Processing for Conversational AI","author":"Ribeiro","year":"2021"},{"key":"2024030820554200400_bib51","doi-asserted-by":"publisher","first-page":"4269","DOI":"10.18653\/v1\/2021.emnlp-main.351","article-title":"Structural adapters in pretrained\n                        language models for amr-to-text generation","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural\n                        Language Processing","author":"Ribeiro","year":"2021"},{"key":"2024030820554200400_bib52","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1162\/tacl_a_00313","article-title":"Leveraging pre-trained checkpoints for\n                        sequence generation tasks","volume":"8","author":"Rothe","year":"2020","journal-title":"Transactions of the\n                        Association for Computational Linguistics"},{"key":"2024030820554200400_bib53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.704","article-title":"Bleurt: Learning robust metrics for text\n                        generation","author":"Sellam","year":"2020","journal-title":"arXiv preprint\n                    arXiv:2004.04696"},{"key":"2024030820554200400_bib54","doi-asserted-by":"publisher","first-page":"1861","DOI":"10.1145\/3397271.3401289","article-title":"G2t: Generating fluent descriptions for knowledge\n                        graph","volume-title":"Proceedings of the 43rd International ACM\n                        SIGIR Conference on Research and Development in Information\n                        Retrieval","author":"Shi","year":"2020"},{"key":"2024030820554200400_bib55","unstructured":"Mathew\n              Snover\n            ,\n                                BonnieDorr,\n                                RichardSchwartz,\n                                JohnMakhoul,\n                                LinneaMicciulla, and\n                                RalphWeischedel.\n                        2005. A study of translation error rate with\n                        targeted human annotation, Technical Report\n                        LAMP-TR-126, CS-TR-4755,\n                    UMIACS-TR-2005-58."},{"key":"2024030820554200400_bib56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1150","article-title":"A graph-to-sequence model for amr-to-text\n                        generation","volume-title":"ACL","author":"Song","year":"2018"},{"key":"2024030820554200400_bib57","first-page":"895","article-title":"Plan-then-generate: Controlled\n                        data-to-text generation via planning","volume-title":"Findings of\n                        the Association for Computational Linguistics: EMNLP 2021","author":"Yixuan","year":"2021"},{"key":"2024030820554200400_bib58","first-page":"3104","article-title":"Sequence to sequence learning with neural\n                        networks","volume-title":"Advances in Neural Information\n                        Processing Systems 27: Annual Conference on Neural Information Processing\n                        Systems 2014, December 8\u201313 2014, Montreal, Quebec, Canada","author":"Sutskever","year":"2014"},{"key":"2024030820554200400_bib59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.558","article-title":"Mvp: Multi-task supervised pre-training for natural language\n                        generation","author":"Tang","year":"2022","journal-title":"arXiv preprint\n                    arXiv:2206.12131"},{"key":"2024030820554200400_bib60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.371","article-title":"Robust (controlled) table-to-text generation with\n                        structure-aware equivariance learning","author":"Wang","year":"2022","journal-title":"arXiv\n                        preprint arXiv:2205.03972"},{"key":"2024030820554200400_bib61","doi-asserted-by":"publisher","first-page":"4831","DOI":"10.18653\/v1\/2021.findings-acl.427","article-title":"Sketch and refine: Towards faithful and informative\n                        table-to-text generation","volume-title":"Findings of the\n                        Association for Computational Linguistics: ACL\/IJCNLP 2021, Online Event,\n                        August 1\u20136, 2021","author":"Wang","year":"2021"},{"key":"2024030820554200400_bib62","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1162\/tacl_a_00297","article-title":"Amr-to-text generation with graph\n                    transformer","volume":"8","author":"Wang","year":"2020","journal-title":"Transactions of the Association for\n                        Computational Linguistics"},{"key":"2024030820554200400_bib63","doi-asserted-by":"publisher","first-page":"2273","DOI":"10.18653\/v1\/2021.findings-acl.200","article-title":"Structure-aware pre-training for table-to-text\n                        generation","volume-title":"Findings of the Association for\n                        Computational Linguistics: ACL-IJCNLP 2021","author":"Xing","year":"2021"},{"key":"2024030820554200400_bib64","doi-asserted-by":"publisher","first-page":"1962","DOI":"10.18653\/v1\/D19-1204","article-title":"CoSQL: A conversational text-to-SQL challenge\n                        towards cross-domain natural language interfaces to\n                        databases","volume-title":"Proceedings of the 2019 Conference on\n                        Empirical Methods in Natural Language Processing and the 9th International\n                        Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Tao","year":"2019"},{"key":"2024030820554200400_bib65","first-page":"186","article-title":"WebNLG challenge 2020: Language agnostic\n                        delexicalisation for multilingual RDF-to-text generation","volume-title":"Proceedings of the 3rd International Workshop on Natural Language\n                        Generation from the Semantic Web (WebNLG+)","author":"Zhou","year":"2020"},{"key":"2024030820554200400_bib66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1548","article-title":"Modeling graph structure in transformer for better\n                        amr-to-text generation","volume-title":"EMNLP-IJCNLP","author":"Zhu","year":"2019"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00641\/2346090\/tacl_a_00641.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00641\/2346090\/tacl_a_00641.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T15:56:05Z","timestamp":1709913365000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00641\/119991\/Unifying-Structured-Data-as-Graph-for-Data-to-Text"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00641","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024]]},"published":{"date-parts":[[2024]]}}}