{"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/variational-neural-discourse-relation","title":"Variational Neural Discourse Relation Recognizer","arxiv_id":"1603.03876","date":"2016-03-12","proceeding":"EMNLP 2016 11","authors":["Biao Zhang","Deyi Xiong","Jinsong Su","Qun Liu","Rongrong Ji","Hong Duan","Min Zhang"],"abstract":"Implicit discourse relation recognition is a crucial component for automatic\ndiscourselevel analysis and nature language understanding. Previous studies\nexploit discriminative models that are built on either powerful manual features\nor deep discourse representations. In this paper, instead, we explore\ngenerative models and propose a variational neural discourse relation\nrecognizer. We refer to this model as VarNDRR. VarNDRR establishes a directed\nprobabilistic model with a latent continuous variable that generates both a\ndiscourse and the relation between the two arguments of the discourse. In order\nto perform efficient inference and learning, we introduce neural discourse\nrelation models to approximate the prior and posterior distributions of the\nlatent variable, and employ these approximated distributions to optimize a\nreparameterized variational lower bound. This allows VarNDRR to be trained with\nstandard stochastic gradient methods. Experiments on the benchmark data set\nshow that VarNDRR can achieve comparable results against stateof- the-art\nbaselines without using any manual features.","url_abs":"http://arxiv.org/abs/1603.03876v2","url_pdf":"http://arxiv.org/pdf/1603.03876v2.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":"variational-neural-discourse-relation","repo_url":"https://github.com/DeepLearnXMU/VarNDRR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"Relation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}