Generative Model Using Knowledge Graph for Document-Grounded Conversations
Document-grounded conversation (DGC) is a natural language generation task to generate fluent and informative responses by leveraging dialogue history and document(s). Recently, DGCs have focused on fine-tuning using pretrained language models. However, these approaches have a problem in that they m...
Main Authors: | Kim, B. (Author), Kim, D. (Author), Kim, H. (Author), Kim, S. (Author), Kwon, O.-W (Author), Lee, D. (Author) |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI
2022
|
Subjects: | |
Online Access: | View Fulltext in Publisher |
Similar Items
-
Determination and Testing the Domination Numbers of Helm Graph, Web Graph and Levi Graph Using MATLAB
by: Ayhan khalil
Published: (1999-11-01) -
Extractive multi-document text summarization based on graph independent sets
by: Taner Uçkan, et al.
Published: (2020-09-01) -
Multiscale planar graph generation
by: Varsha Chauhan, et al.
Published: (2019-07-01) -
Generation of colored graphs with isomorphism rejection
by: Razumovsky, Peter Vladimirovich, et al.
Published: (2021-05-01) -
Incorporating External Knowledge into Unsupervised Graph Model for Document Summarization
by: Tiancheng Tang, et al.
Published: (2020-09-01)