{"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/asking-the-right-question-inferring-advice","title":"Asking the Right Question: Inferring Advice-Seeking Intentions from Personal Narratives","arxiv_id":"1904.01587","date":"2019-04-02","proceeding":"NAACL 2019 6","authors":["Liye Fu","Jonathan P. Chang","Cristian Danescu-Niculescu-Mizil"],"abstract":"People often share personal narratives in order to seek advice from others.\nTo properly infer the narrator's intention, one needs to apply a certain degree\nof common sense and social intuition. To test the capabilities of NLP systems\nto recover such intuition, we introduce the new task of inferring what is the\nadvice-seeking goal behind a personal narrative. We formulate this as a cloze\ntest, where the goal is to identify which of two advice-seeking questions was\nremoved from a given narrative.\n  The main challenge in constructing this task is finding pairs of semantically\nplausible advice-seeking questions for given narratives. To address this\nchallenge, we devise a method that exploits commonalities in experiences people\nshare online to automatically extract pairs of questions that are appropriate\ncandidates for the cloze task. This results in a dataset of over 20,000\npersonal narratives, each matched with a pair of related advice-seeking\nquestions: one actually intended by the narrator, and the other one not. The\ndataset covers a very broad array of human experiences, from dating, to career\noptions, to stolen iPads. We use human annotation to determine the degree to\nwhich the task relies on common sense and social intuition in addition to a\nsemantic understanding of the narrative. By introducing several baselines for\nthis new task we demonstrate its feasibility and identify avenues for better\nmodeling the intention of the narrator.","url_abs":"http://arxiv.org/abs/1904.01587v1","url_pdf":"http://arxiv.org/pdf/1904.01587v1.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":"asking-the-right-question-inferring-advice","repo_url":"https://github.com/CornellNLP/ASQ","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"cloze-test","task_name":"Cloze Test"},{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"}],"methods":[],"datasets_introduced":[{"slug":"advice-seeking-questions","name":"Advice Seeking Questions","full_name":null}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.01587","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}