{"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/a-skeleton-based-model-for-promoting","title":"A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation","arxiv_id":"1808.06945","date":"2018-08-21","proceeding":"EMNLP 2018 10","authors":["Jingjing Xu","Xuancheng Ren","Yi Zhang","Qi Zeng","Xiaoyan Cai","Xu sun"],"abstract":"Narrative story generation is a challenging problem because it demands the\ngenerated sentences with tight semantic connections, which has not been well\nstudied by most existing generative models. To address this problem, we propose\na skeleton-based model to promote the coherence of generated stories. Different\nfrom traditional models that generate a complete sentence at a stroke, the\nproposed model first generates the most critical phrases, called skeleton, and\nthen expands the skeleton to a complete and fluent sentence. The skeleton is\nnot manually defined, but learned by a reinforcement learning method. Compared\nto the state-of-the-art models, our skeleton-based model can generate\nsignificantly more coherent text according to human evaluation and automatic\nevaluation. The G-score is improved by 20.1% in the human evaluation. The code\nis available at https://github.com/lancopku/Skeleton-Based-Generation-Model","url_abs":"http://arxiv.org/abs/1808.06945v2","url_pdf":"http://arxiv.org/pdf/1808.06945v2.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":"a-skeleton-based-model-for-promoting","repo_url":"https://github.com/lancopku/Skeleton-Based-Generation-Model","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"story-generation","task_name":"Story Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.06945","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}