CKG: Dynamic Representation Based on Context and Knowledge Graph

Tang, Xunzhu; Sun, Tiezhu; Zhu, Rujie; Wang, Shi

doi:10.1109/icpr48806.2021.9412877

Cited by 4 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and some previous methods have made many improvements to this issue. Knowled-GPT uses reinforcement learning for knowledge selection [23,28,31] and feed knowledge as input of the model. Knowledge Grounded Blender focuses on fixing the problem of how to supply the knowledge of seen entities [31].…”

Section: Introductionmentioning

confidence: 99%

GE-Blender: Graph-Based Knowledge Enhancement for Blender

Lian¹,

Tang²,

Wang³

2023

Preprint

View full text Add to dashboard Cite

Although the great success of open-domain dialogue generation, unseen entities can have a large impact on the dialogue generation task. It leads to performance degradation of the model in the dialog generation. Previous researches used retrieved knowledge of seen entities as the auxiliary data to enhance the representation of the model. Nevertheless, logical explanation of unseen entities remains unexplored, such as possible co-occurrence or semantically similar words of them and their entity category. In this work, we propose an approach to address the challenge above. We construct a graph by extracting entity nodes in them, enhancing the representation of the context of the unseen entity with the entity's 1-hop surrounding nodes. Furthermore, We added the named entity tag prediction task to apply the problem that the unseen entity does not exist in the graph. We conduct our experiments on an open dataset Wizard of Wikipedia and the empirical results indicate that our approach outperforms the state-of-the-art approaches on Wizard of Wikipedia.

show abstract