{"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-corpus-and-evaluation-framework-for-deeper","title":"A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories","arxiv_id":"1604.01696","date":"2016-04-06","proceeding":null,"authors":["Nasrin Mostafazadeh","Nathanael Chambers","Xiaodong He","Devi Parikh","Dhruv Batra","Lucy Vanderwende","Pushmeet Kohli","James Allen"],"abstract":"Representation and learning of commonsense knowledge is one of the\nfoundational problems in the quest to enable deep language understanding. This\nissue is particularly challenging for understanding casual and correlational\nrelationships between events. While this topic has received a lot of interest\nin the NLP community, research has been hindered by the lack of a proper\nevaluation framework. This paper attempts to address this problem with a new\nframework for evaluating story understanding and script learning: the 'Story\nCloze Test'. This test requires a system to choose the correct ending to a\nfour-sentence story. We created a new corpus of ~50k five-sentence commonsense\nstories, ROCStories, to enable this evaluation. This corpus is unique in two\nways: (1) it captures a rich set of causal and temporal commonsense relations\nbetween daily events, and (2) it is a high quality collection of everyday life\nstories that can also be used for story generation. Experimental evaluation\nshows that a host of baselines and state-of-the-art models based on shallow\nlanguage understanding struggle to achieve a high score on the Story Cloze\nTest. We discuss these implications for script and story learning, and offer\nsuggestions for deeper language understanding.","url_abs":"http://arxiv.org/abs/1604.01696v1","url_pdf":"http://arxiv.org/pdf/1604.01696v1.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":[],"tasks":[{"task_slug":"cloze-test","task_name":"Cloze Test"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"story-generation","task_name":"Story Generation"}],"methods":[],"datasets_introduced":[{"slug":"storycloze","name":"StoryCloze","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1604.01696","atlas_url":"https://app.syntology.ai/?focus=1604.01696","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}