{"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/grape-knowledge-graph-enhanced-passage-reader","title":"Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering","arxiv_id":"2210.02933","date":"2022-10-06","proceeding":null,"authors":["Mingxuan Ju","Wenhao Yu","Tong Zhao","Chuxu Zhang","Yanfang Ye"],"abstract":"A common thread of open-domain question answering (QA) models employs a retriever-reader pipeline that first retrieves a handful of relevant passages from Wikipedia and then peruses the passages to produce an answer. However, even state-of-the-art readers fail to capture the complex relationships between entities appearing in questions and retrieved passages, leading to answers that contradict the facts. In light of this, we propose a novel knowledge Graph enhanced passage reader, namely Grape, to improve the reader performance for open-domain QA. Specifically, for each pair of question and retrieved passage, we first construct a localized bipartite graph, attributed to entity embeddings extracted from the intermediate layer of the reader model. Then, a graph neural network learns relational knowledge while fusing graph and contextual representations into the hidden states of the reader model. Experiments on three open-domain QA benchmarks show Grape can improve the state-of-the-art performance by up to 2.2 exact match score with a negligible overhead increase, with the same retriever and retrieved passages. Our code is publicly available at https://github.com/jumxglhf/GRAPE.","url_abs":"https://arxiv.org/abs/2210.02933v2","url_pdf":"https://arxiv.org/pdf/2210.02933v2.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":"grape-knowledge-graph-enhanced-passage-reader","repo_url":"https://github.com/jumxglhf/grape","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"entity-embeddings","task_name":"Entity Embeddings"},{"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.02933","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}