{"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/deep-multitask-learning-for-semantic","title":"Deep Multitask Learning for Semantic Dependency Parsing","arxiv_id":"1704.06855","date":"2017-04-22","proceeding":"ACL 2017 7","authors":["Hao Peng","Sam Thomson","Noah A. Smith"],"abstract":"We present a deep neural architecture that parses sentences into three\nsemantic dependency graph formalisms. By using efficient, nearly arc-factored\ninference and a bidirectional-LSTM composed with a multi-layer perceptron, our\nbase system is able to significantly improve the state of the art for semantic\ndependency parsing, without using hand-engineered features or syntax. We then\nexplore two multitask learning approaches---one that shares parameters across\nformalisms, and one that uses higher-order structures to predict the graphs\njointly. We find that both approaches improve performance across formalisms on\naverage, achieving a new state of the art. Our code is open-source and\navailable at https://github.com/Noahs-ARK/NeurboParser.","url_abs":"http://arxiv.org/abs/1704.06855v2","url_pdf":"http://arxiv.org/pdf/1704.06855v2.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":"deep-multitask-learning-for-semantic","repo_url":"https://github.com/Noahs-ARK/NeurboParser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"arc","task_name":"ARC"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"semantic-dependency-parsing","task_name":"Semantic Dependency Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.06855","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}