{"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/automatic-event-salience-identification","title":"Automatic Event Salience Identification","arxiv_id":"1809.00647","date":"2018-09-03","proceeding":"EMNLP 2018 10","authors":["Zhengzhong Liu","Chenyan Xiong","Teruko Mitamura","Eduard Hovy"],"abstract":"Identifying the salience (i.e. importance) of discourse units is an important\ntask in language understanding. While events play important roles in text\ndocuments, little research exists on analyzing their saliency status. This\npaper empirically studies the Event Salience task and proposes two salience\ndetection models based on content similarities and discourse relations. The\nfirst is a feature based salience model that incorporates similarities among\ndiscourse units. The second is a neural model that captures more complex\nrelations between discourse units. Tested on our new large-scale event salience\ncorpus, both methods significantly outperform the strong frequency baseline,\nwhile our neural model further improves the feature based one by a large\nmargin. Our analyses demonstrate that our neural model captures interesting\nconnections between salience and discourse unit relations (e.g., scripts and\nframe structures).","url_abs":"http://arxiv.org/abs/1809.00647v1","url_pdf":"http://arxiv.org/pdf/1809.00647v1.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":"automatic-event-salience-identification","repo_url":"https://github.com/hunterhector/EventSalience","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.00647","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}