{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/table-to-text-generation-by-structure-aware","title":"Table-to-text Generation by Structure-aware Seq2seq Learning","arxiv_id":"1711.09724","date":"2017-11-27","proceeding":null,"authors":["Tianyu Liu","Kexiang Wang","Lei Sha","Baobao Chang","Zhifang Sui"],"abstract":"Table-to-text generation aims to generate a description for a factual table\nwhich can be viewed as a set of field-value records. To encode both the content\nand the structure of a table, we propose a novel structure-aware seq2seq\narchitecture which consists of field-gating encoder and description generator\nwith dual attention. In the encoding phase, we update the cell memory of the\nLSTM unit by a field gate and its corresponding field value in order to\nincorporate field information into table representation. In the decoding phase,\ndual attention mechanism which contains word level attention and field level\nattention is proposed to model the semantic relevance between the generated\ndescription and the table. We conduct experiments on the \\texttt{WIKIBIO}\ndataset which contains over 700k biographies and corresponding infoboxes from\nWikipedia. The attention visualizations and case studies show that our model is\ncapable of generating coherent and informative descriptions based on the\ncomprehensive understanding of both the content and the structure of a table.\nAutomatic evaluations also show our model outperforms the baselines by a great\nmargin. Code for this work is available on\nhttps://github.com/tyliupku/wiki2bio.","url_abs":"http://arxiv.org/abs/1711.09724v1","url_pdf":"http://arxiv.org/pdf/1711.09724v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"table-to-text-generation-by-structure-aware","repo_url":"https://github.com/tyliupku/wiki2bio","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"table-to-text-generation-by-structure-aware","repo_url":"https://github.com/Parth27/Data2Text","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"table-to-text-generation-by-structure-aware","repo_url":"https://github.com/anjbapat/D2T","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"table-to-text-generation","task_name":"Table-to-Text Generation"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/table-to-text-generation-on-wikibio","task":"Table-to-Text Generation","dataset":"WikiBio","model":"Field-gating Seq2seq + dual attention","rank_in_archive_order":1,"of":4,"metrics":{"BLEU":"44.89","ROUGE":"41.21"},"uses_additional_data":false},{"leaderboard":"/sota/table-to-text-generation-on-wikibio","task":"Table-to-Text Generation","dataset":"WikiBio","model":"Field-gating Seq2seq + dual attention + beam search","rank_in_archive_order":2,"of":4,"metrics":{"BLEU":"44.71","ROUGE":"41.65"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.09724","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}