{"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/bag-bi-directional-attention-entity-graph","title":"BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering","arxiv_id":"1904.04969","date":"2019-04-10","proceeding":"NAACL 2019 6","authors":["Yu Cao","Meng Fang","DaCheng Tao"],"abstract":"Multi-hop reasoning question answering requires deep comprehension of\nrelationships between various documents and queries. We propose a\nBi-directional Attention Entity Graph Convolutional Network (BAG), leveraging\nrelationships between nodes in an entity graph and attention information\nbetween a query and the entity graph, to solve this task. Graph convolutional\nnetworks are used to obtain a relation-aware representation of nodes for entity\ngraphs built from documents with multi-level features. Bidirectional attention\nis then applied on graphs and queries to generate a query-aware nodes\nrepresentation, which will be used for the final prediction. Experimental\nevaluation shows BAG achieves state-of-the-art accuracy performance on the\nQAngaroo WIKIHOP dataset.","url_abs":"http://arxiv.org/abs/1904.04969v1","url_pdf":"http://arxiv.org/pdf/1904.04969v1.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":"bag-bi-directional-attention-entity-graph","repo_url":"https://github.com/caoyu1991/BAG","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.04969","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}