TY - GEN
T1 - Graph-Structured Context Understanding for Knowledge-grounded Response Generation
AU - Li, Yanran
AU - Li, Wenjie
AU - Wang, Zhitao
N1 - Funding Information:
The work described in this paper was supported by Research Grants Council of Hong Kong (152040/18E 15207920), National Natural Science Foundation of China (62076212), Huawei Collaborative Research Grant (ZG7H) and The Hong Kong Polytechnic University (ZVQ0).
Publisher Copyright:
© 2021 ACM.
PY - 2021/7/11
Y1 - 2021/7/11
N2 - In this work, we establish a context graph from both conversation utterances and external knowledge, and develop a novel graph-based encoder to better understand the conversation context. Specifically, the encoder fuses the information in the context graph stage-by-stage and provides global context-graph-aware representations of each node in the graph to facilitate knowledge-grounded response generation. On a large-scale conversation corpus, we validate the effectiveness of the proposed approach and demonstrate the benefit of knowledge in conversation understanding.
AB - In this work, we establish a context graph from both conversation utterances and external knowledge, and develop a novel graph-based encoder to better understand the conversation context. Specifically, the encoder fuses the information in the context graph stage-by-stage and provides global context-graph-aware representations of each node in the graph to facilitate knowledge-grounded response generation. On a large-scale conversation corpus, we validate the effectiveness of the proposed approach and demonstrate the benefit of knowledge in conversation understanding.
KW - dialogue systems
KW - knowledge-grounded response generation
UR - http://www.scopus.com/inward/record.url?scp=85111641849&partnerID=8YFLogxK
U2 - 10.1145/3404835.3463000
DO - 10.1145/3404835.3463000
M3 - Conference article published in proceeding or book
AN - SCOPUS:85111641849
T3 - SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval
SP - 1930
EP - 1934
BT - SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval
PB - Association for Computing Machinery, Inc
T2 - 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2021
Y2 - 11 July 2021 through 15 July 2021
ER -