{"type":"ScholarlyArticle","title":"Knowledge-Aware Dialogue Generation via Hierarchical Infobox Accessing and Infobox-Dialogue Interaction Graph Network","authors":[{"name":"Sixing Wu","slug":"sixing-wu","given":"Sixing","family":"Wu","affiliation":""},{"name":"Minghui Wang","slug":"minghui-wang","given":"Minghui","family":"Wang","affiliation":""},{"name":"Dawei Zhang","slug":"dawei-zhang","given":"Dawei","family":"Zhang","affiliation":""},{"name":"Yang Zhou","slug":"yang-zhou","given":"Yang","family":"Zhou","affiliation":""},{"name":"Ying Li","slug":"ying-li","given":"Ying","family":"Li","affiliation":""},{"name":"Zhonghai Wu","slug":"zhonghai-wu","given":"Zhonghai","family":"Wu","affiliation":""}],"abstract":"Due to limited knowledge carried by queries, traditional dialogue systems often face the dilemma of generating boring responses, leading to poor user experience. To alleviate this issue, this paper proposes a novel infobox knowledge-aware dialogue generation approach, HITA-Graph, with three unique features. First, open-domain infobox tables that describe entities with relevant attributes are adopted as the knowledge source. An order-irrelevance Hierarchical Infobox Table Encoder is proposed to represent an infobox table at three levels of granularity. In addition, an Infobox-Dialogue Interaction Graph Network is built to effectively integrate the infobox context and the dialogue context into a unified infobox representation. Second, a Hierarchical Infobox Attribute Attention mechanism is developed to  access the encoded infobox knowledge at different levels of granularity. Last but not least, a Dynamic Mode Fusion strategy is designed to allow the Decoder to select a vocabulary word or copy a word from the given infobox/query. We extract infobox tables from Chinese Wikipedia and construct an infobox knowledge base. Extensive evaluation on an open-released Chinese corpus demonstrates the superior performance of our approach against several representative methods.","doi":"10.24963/ijcai.2021/546","url":"https://ijcai.org/proceedings/2021/546","pdf":"https://ijcai.org/proceedings/2021/0546.pdf","markdown":"https://ijcai.org/proceedings/2021/546.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/546","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Natural Language Processing","track":"Main Track","number":546,"pages":{"first":3964,"last":3970},"keywords":["Natural Language Processing: Natural Language Generation","Natural Language Processing: Dialogue"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}