{"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/implicit-argument-prediction-with-event","title":"Implicit Argument Prediction with Event Knowledge","arxiv_id":"1802.07226","date":"2018-02-20","proceeding":"NAACL 2018 6","authors":["Pengxiang Cheng","Katrin Erk"],"abstract":"Implicit arguments are not syntactically connected to their predicates, and\nare therefore hard to extract. Previous work has used models with large numbers\nof features, evaluated on very small datasets. We propose to train models for\nimplicit argument prediction on a simple cloze task, for which data can be\ngenerated automatically at scale. This allows us to use a neural model, which\ndraws on narrative coherence and entity salience for predictions. We show that\nour model has superior performance on both synthetic and natural data.","url_abs":"http://arxiv.org/abs/1802.07226v2","url_pdf":"http://arxiv.org/pdf/1802.07226v2.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":"implicit-argument-prediction-with-event","repo_url":"https://github.com/pxch/event_imp_arg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.07226","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}