{"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/neural-ranking-models-for-temporal-dependency","title":"Neural Ranking Models for Temporal Dependency Structure Parsing","arxiv_id":"1809.00370","date":"2018-09-02","proceeding":"EMNLP 2018 10","authors":["Yuchen Zhang","Nianwen Xue"],"abstract":"We design and build the first neural temporal dependency parser. It utilizes\na neural ranking model with minimal feature engineering, and parses time\nexpressions and events in a text into a temporal dependency tree structure. We\nevaluate our parser on two domains: news reports and narrative stories. In a\nparsing-only evaluation setup where gold time expressions and events are\nprovided, our parser reaches 0.81 and 0.70 f-score on unlabeled and labeled\nparsing respectively, a result that is very competitive against alternative\napproaches. In an end-to-end evaluation setup where time expressions and events\nare automatically recognized, our parser beats two strong baselines on both\ndata domains. Our experimental results and discussions shed light on the nature\nof temporal dependency structures in different domains and provide insights\nthat we believe will be valuable to future research in this area.","url_abs":"http://arxiv.org/abs/1809.00370v1","url_pdf":"http://arxiv.org/pdf/1809.00370v1.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":"neural-ranking-models-for-temporal-dependency","repo_url":"https://github.com/yuchenz/tdp_ranking","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"neural-ranking-models-for-temporal-dependency","repo_url":"https://github.com/bnmin/tdp_ranking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"feature-engineering","task_name":"Feature Engineering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.00370","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}