{"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/pomo-generating-entity-specific-post","title":"PoMo: Generating Entity-Specific Post-Modifiers in Context","arxiv_id":"1904.03111","date":"2019-04-05","proceeding":"NAACL 2019 6","authors":["Jun Seok Kang","Robert L. Logan IV","Zewei Chu","Yang Chen","Dheeru Dua","Kevin Gimpel","Sameer Singh","Niranjan Balasubramanian"],"abstract":"We introduce entity post-modifier generation as an instance of a\ncollaborative writing task. Given a sentence about a target entity, the task is\nto automatically generate a post-modifier phrase that provides contextually\nrelevant information about the entity. For example, for the sentence, \"Barack\nObama, _______, supported the #MeToo movement.\", the phrase \"a father of two\ngirls\" is a contextually relevant post-modifier. To this end, we build PoMo, a\npost-modifier dataset created automatically from news articles reflecting a\njournalistic need for incorporating entity information that is relevant to a\nparticular news event. PoMo consists of more than 231K sentences with\npost-modifiers and associated facts extracted from Wikidata for around 57K\nunique entities. We use crowdsourcing to show that modeling contextual\nrelevance is necessary for accurate post-modifier generation. We adapt a number\nof existing generation approaches as baselines for this dataset. Our results\nshow there is large room for improvement in terms of both identifying relevant\nfacts to include (knowing which claims are relevant gives a >20% improvement in\nBLEU score), and generating appropriate post-modifier text for the context\n(providing relevant claims is not sufficient for accurate generation). We\nconduct an error analysis that suggests promising directions for future\nresearch.","url_abs":"http://arxiv.org/abs/1904.03111v2","url_pdf":"http://arxiv.org/pdf/1904.03111v2.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":"articles","task_name":"Articles"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[{"slug":"pomo","name":"PoMo","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.03111","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}