{"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/tracking-state-changes-in-procedural-text-a","title":"Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehension","arxiv_id":"1805.06975","date":"2018-05-17","proceeding":"NAACL 2018 6","authors":["Bhavana Dalvi Mishra","Lifu Huang","Niket Tandon","Wen-tau Yih","Peter Clark"],"abstract":"We present a new dataset and models for comprehending paragraphs about\nprocesses (e.g., photosynthesis), an important genre of text describing a\ndynamic world. The new dataset, ProPara, is the first to contain natural\n(rather than machine-generated) text about a changing world along with a full\nannotation of entity states (location and existence) during those changes (81k\ndatapoints). The end-task, tracking the location and existence of entities\nthrough the text, is challenging because the causal effects of actions are\noften implicit and need to be inferred. We find that previous models that have\nworked well on synthetic data achieve only mediocre performance on ProPara, and\nintroduce two new neural models that exploit alternative mechanisms for state\nprediction, in particular using LSTM input encoding and span prediction. The\nnew models improve accuracy by up to 19%. The dataset and models are available\nto the community at http://data.allenai.org/propara.","url_abs":"http://arxiv.org/abs/1805.06975v1","url_pdf":"http://arxiv.org/pdf/1805.06975v1.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":"procedural-text-understanding","task_name":"Procedural Text Understanding"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[{"slug":"propara","name":"ProPara","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.06975","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}