{"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/story-ending-generation-with-incremental","title":"Story Ending Generation with Incremental Encoding and Commonsense Knowledge","arxiv_id":"1808.10113","date":"2018-08-30","proceeding":null,"authors":["Jian Guan","Yansen Wang","Minlie Huang"],"abstract":"Generating a reasonable ending for a given story context, i.e., story ending\ngeneration, is a strong indication of story comprehension. This task requires\nnot only to understand the context clues which play an important role in\nplanning the plot but also to handle implicit knowledge to make a reasonable,\ncoherent story.\n  In this paper, we devise a novel model for story ending generation. The model\nadopts an incremental encoding scheme to represent context clues which are\nspanning in the story context. In addition, commonsense knowledge is applied\nthrough multi-source attention to facilitate story comprehension, and thus to\nhelp generate coherent and reasonable endings. Through building context clues\nand using implicit knowledge, the model is able to produce reasonable story\nendings. context clues implied in the post and make the inference based on it.\n  Automatic and manual evaluation shows that our model can generate more\nreasonable story endings than state-of-the-art baselines.","url_abs":"http://arxiv.org/abs/1808.10113v3","url_pdf":"http://arxiv.org/pdf/1808.10113v3.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":"story-ending-generation-with-incremental","repo_url":"https://github.com/JianGuanTHU/StoryEndGen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-guided-story-ending-generation","task_name":"Image-guided Story Ending Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-guided-story-ending-generation-on-vist","task":"Image-guided Story Ending Generation","dataset":"VIST-E","model":"IE+MSA","rank_in_archive_order":3,"of":6,"metrics":{"BLEU-1":"19.15","BLEU-2":"5.74","BLEU-3":"2.73","BLEU-4":"1.63","CIDEr":"15.56","METEOR":"6.59","ROUGE-L":"20.62"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.10113","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}