{"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/multi-paragraph-reasoning-with-knowledge","title":"Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network","arxiv_id":"1911.02170","date":"2019-11-06","proceeding":null,"authors":["Deming Ye","Yankai Lin","Zheng-Hao Liu","Zhiyuan Liu","Maosong Sun"],"abstract":"Multi-paragraph reasoning is indispensable for open-domain question answering (OpenQA), which receives less attention in the current OpenQA systems. In this work, we propose a knowledge-enhanced graph neural network (KGNN), which performs reasoning over multiple paragraphs with entities. To explicitly capture the entities' relatedness, KGNN utilizes relational facts in knowledge graph to build the entity graph. The experimental results show that KGNN outperforms in both distractor and full wiki settings than baselines methods on HotpotQA dataset. And our further analysis illustrates KGNN is effective and robust with more retrieved paragraphs.","url_abs":"https://arxiv.org/abs/1911.02170v1","url_pdf":"https://arxiv.org/pdf/1911.02170v1.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":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-hotpotqa","task":"Question Answering","dataset":"HotpotQA","model":"KGNN","rank_in_archive_order":58,"of":72,"metrics":{"ANS-EM":"0.277","ANS-F1":"0.372","JOINT-EM":"0.070","JOINT-F1":"0.247","SUP-EM":"0.127","SUP-F1":"0.472"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.02170","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}