{"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/dating-documents-using-graph-convolution","title":"Dating Documents using Graph Convolution Networks","arxiv_id":"1902.00175","date":"2019-02-01","proceeding":"ACL 2018 7","authors":["Shikhar Vashishth","Shib Sankar Dasgupta","Swayambhu Nath Ray","Partha Talukdar"],"abstract":"Document date is essential for many important tasks, such as document\nretrieval, summarization, event detection, etc. While existing approaches for\nthese tasks assume accurate knowledge of the document date, this is not always\navailable, especially for arbitrary documents from the Web. Document Dating is\na challenging problem which requires inference over the temporal structure of\nthe document. Prior document dating systems have largely relied on handcrafted\nfeatures while ignoring such document internal structures. In this paper, we\npropose NeuralDater, a Graph Convolutional Network (GCN) based document dating\napproach which jointly exploits syntactic and temporal graph structures of\ndocument in a principled way. To the best of our knowledge, this is the first\napplication of deep learning for the problem of document dating. Through\nextensive experiments on real-world datasets, we find that NeuralDater\nsignificantly outperforms state-of-the-art baseline by 19% absolute (45%\nrelative) accuracy points.","url_abs":"http://arxiv.org/abs/1902.00175v1","url_pdf":"http://arxiv.org/pdf/1902.00175v1.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":"dating-documents-using-graph-convolution","repo_url":"https://github.com/malllabiisc/NeuralDater","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"document-dating","task_name":"Document Dating"},{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/document-dating-on-apw","task":"Document Dating","dataset":"APW","model":"NeuralDater","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"64.1"},"uses_additional_data":false},{"leaderboard":"/sota/document-dating-on-nyt","task":"Document Dating","dataset":"NYT","model":"NeuralDater","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"58.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.00175","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}