@article{M8C9E4A8F,
title = "Structuralized External Knowledge and Multi-task Learning for Knowledge Selection",
journal = "Journal of KIISE, JOK",
year = "2022",
issn = "2383-630X",
doi = "10.5626/JOK.2022.49.10.884",
author = "Junhee Cho,Youngjoong Ko",
keywords = "task-oriented dialog system,pre-trained language model,multi-task learning,knowledge-grounded dialog",
abstract = "Typically, task-oriented dialog systems use well-structured knowledge, such as databases, to generate the most appropriate responses to users" questions. However, to generate more appropriate and fluent responses, external knowledge, which is unstructured text data such as web data or FAQs, is necessary. In this paper, we propose a novel multi-task learning method with a pre-trained language model and a graph neural network. The proposed method makes the system select the external knowledge effectively by not only understanding linguistic information but also grasping the structural information latent in external knowledge which is converted into structured data, graphs, using a dependency parser. Experimental results show that our proposed method obtains higher performance than the traditional bi-encoder or cross-encoder methods that use pre-trained language models."
}