{"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/improving-question-answering-over-incomplete","title":"Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader","arxiv_id":"1905.07098","date":"2019-05-17","proceeding":"ACL 2019 7","authors":["Wenhan Xiong","Mo Yu","Shiyu Chang","Xiaoxiao Guo","William Yang Wang"],"abstract":"We propose a new end-to-end question answering model, which learns to aggregate answer evidence from an incomplete knowledge base (KB) and a set of retrieved text snippets. Under the assumptions that the structured KB is easier to query and the acquired knowledge can help the understanding of unstructured text, our model first accumulates knowledge of entities from a question-related KB subgraph; then reformulates the question in the latent space and reads the texts with the accumulated entity knowledge at hand. The evidence from KB and texts are finally aggregated to predict answers. On the widely-used KBQA benchmark WebQSP, our model achieves consistent improvements across settings with different extents of KB incompleteness.","url_abs":"https://arxiv.org/abs/1905.07098v2","url_pdf":"https://arxiv.org/pdf/1905.07098v2.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":"improving-question-answering-over-incomplete","repo_url":"https://github.com/xwhan/Knowledge-Aware-Reader","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"improving-question-answering-over-incomplete","repo_url":"https://github.com/dujiaxin/Knowledge-Aware-Reader","is_official":0,"mentioned_in_paper":0,"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=1905.07098","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}