{"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/dragnn-a-transition-based-framework-for","title":"DRAGNN: A Transition-based Framework for Dynamically Connected Neural Networks","arxiv_id":"1703.04474","date":"2017-03-13","proceeding":null,"authors":["Lingpeng Kong","Chris Alberti","Daniel Andor","Ivan Bogatyy","David Weiss"],"abstract":"In this work, we present a compact, modular framework for constructing novel\nrecurrent neural architectures. Our basic module is a new generic unit, the\nTransition Based Recurrent Unit (TBRU). In addition to hidden layer\nactivations, TBRUs have discrete state dynamics that allow network connections\nto be built dynamically as a function of intermediate activations. By\nconnecting multiple TBRUs, we can extend and combine commonly used\narchitectures such as sequence-to-sequence, attention mechanisms, and\nre-cursive tree-structured models. A TBRU can also serve as both an encoder for\ndownstream tasks and as a decoder for its own task simultaneously, resulting in\nmore accurate multi-task learning. We call our approach Dynamic Recurrent\nAcyclic Graphical Neural Networks, or DRAGNN. We show that DRAGNN is\nsignificantly more accurate and efficient than seq2seq with attention for\nsyntactic dependency parsing and yields more accurate multi-task learning for\nextractive summarization tasks.","url_abs":"http://arxiv.org/abs/1703.04474v1","url_pdf":"http://arxiv.org/pdf/1703.04474v1.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":"dragnn-a-transition-based-framework-for","repo_url":"https://github.com/tensorflow/models/tree/master/research/syntaxnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"extractive-summarization","task_name":"Extractive Summarization"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.04474","atlas_url":"https://app.syntology.ai/?focus=1703.04474","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}