{"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-net-models-for-open-domain-discourse","title":"Neural Net Models for Open-Domain Discourse Coherence","arxiv_id":"1606.01545","date":"2016-06-05","proceeding":null,"authors":["Jiwei Li","Dan Jurafsky"],"abstract":"Discourse coherence is strongly associated with text quality, making it\nimportant to natural language generation and understanding. Yet existing models\nof coherence focus on measuring individual aspects of coherence (lexical\noverlap, rhetorical structure, entity centering) in narrow domains.\n  In this paper, we describe domain-independent neural models of discourse\ncoherence that are capable of measuring multiple aspects of coherence in\nexisting sentences and can maintain coherence while generating new sentences.\nWe study both discriminative models that learn to distinguish coherent from\nincoherent discourse, and generative models that produce coherent text,\nincluding a novel neural latent-variable Markovian generative model that\ncaptures the latent discourse dependencies between sentences in a text.\n  Our work achieves state-of-the-art performance on multiple coherence\nevaluations, and marks an initial step in generating coherent texts given\ndiscourse contexts.","url_abs":"http://arxiv.org/abs/1606.01545v3","url_pdf":"http://arxiv.org/pdf/1606.01545v3.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-net-models-for-open-domain-discourse","repo_url":"https://github.com/karins/CoherenceFramework","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1606.01545","atlas_url":"https://app.syntology.ai/?focus=1606.01545","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}