CogNLG: Cognitive Graph for KG-to-text Generation

Peichao Lai; Feiyang  Ye; Yang-Geng  Fu; Zhiwei  Chen; Yingjie  Wu; Yilei  Wang; Victor Chang

doi:10.1111/exsy.13461

CogNLG: Cognitive Graph for KG-to-text Generation

Peichao Lai, Feiyang Ye, Yang-Geng Fu, Zhiwei Chen, Yingjie Wu, Yilei Wang, Victor Chang^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

Knowledge graph (KG) has been fully considered in natural language generation (NLG) tasks. A KG can help models generate controllable text and achieve better performance. However, most existing related approaches still lack explainability and scalability in large-scale knowledge reasoning. In this work, we propose a novel CogNLG framework for KG-to-text generation tasks. Our CogNLG is implemented based on the dual-process theory in cognitive science. It consists of two systems: one system acts as the analytic system for knowledge extraction, and another is the perceptual system for text generation by using existing knowledge. During text generation, CogNLG provides a visible and explainable reasoning path. Our framework shows excellent performance on all datasets and achieves a BLEU score of 36.7, which increases by 6.7 compared to the best competitor.

Original language	English
Article number	e13461
Journal	Expert Systems
Volume	41
Issue number	1
Early online date	10 Oct 2023
DOIs	https://doi.org/10.1111/exsy.13461
Publication status	Published - Jan 2024

Bibliographical note

© 2023 The Authors. Expert Systems published by John Wiley & Sons Ltd.

This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Keywords

KG-to-text
cognitive graph
natural language generation

Access to Document

10.1111/exsy.13461Licence: CC BY 4.0

Expert Systems - 2023 - Lai - CogNLG Cognitive graph for KG‐to‐text generation
© 2023 The Authors. Expert Systems published by John Wiley & Sons Ltd. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Final published version, 2.91 MBLicence: CC BY 4.0

Cite this

@article{b72b78d375634a5784e447245f9c66e9,

title = "CogNLG: Cognitive Graph for KG-to-text Generation",

abstract = "Knowledge graph (KG) has been fully considered in natural language generation (NLG) tasks. A KG can help models generate controllable text and achieve better performance. However, most existing related approaches still lack explainability and scalability in large-scale knowledge reasoning. In this work, we propose a novel CogNLG framework for KG-to-text generation tasks. Our CogNLG is implemented based on the dual-process theory in cognitive science. It consists of two systems: one system acts as the analytic system for knowledge extraction, and another is the perceptual system for text generation by using existing knowledge. During text generation, CogNLG provides a visible and explainable reasoning path. Our framework shows excellent performance on all datasets and achieves a BLEU score of 36.7, which increases by 6.7 compared to the best competitor.",

keywords = "KG-to-text, cognitive graph, natural language generation",

author = "Peichao Lai and Feiyang Ye and Yang-Geng Fu and Zhiwei Chen and Yingjie Wu and Yilei Wang and Victor Chang",

note = "{\textcopyright} 2023 The Authors. Expert Systems published by John Wiley & Sons Ltd. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.",

year = "2024",

month = jan,

doi = "10.1111/exsy.13461",

language = "English",

volume = "41",

journal = "Expert Systems",

issn = "0266-4720",

publisher = "Wiley-Blackwell",

number = "1",

}

TY - JOUR

T1 - CogNLG: Cognitive Graph for KG-to-text Generation

AU - Lai, Peichao

AU - Ye, Feiyang

AU - Fu, Yang-Geng

AU - Chen, Zhiwei

AU - Wu, Yingjie

AU - Wang, Yilei

AU - Chang, Victor

N1 - © 2023 The Authors. Expert Systems published by John Wiley & Sons Ltd. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

PY - 2024/1

Y1 - 2024/1

N2 - Knowledge graph (KG) has been fully considered in natural language generation (NLG) tasks. A KG can help models generate controllable text and achieve better performance. However, most existing related approaches still lack explainability and scalability in large-scale knowledge reasoning. In this work, we propose a novel CogNLG framework for KG-to-text generation tasks. Our CogNLG is implemented based on the dual-process theory in cognitive science. It consists of two systems: one system acts as the analytic system for knowledge extraction, and another is the perceptual system for text generation by using existing knowledge. During text generation, CogNLG provides a visible and explainable reasoning path. Our framework shows excellent performance on all datasets and achieves a BLEU score of 36.7, which increases by 6.7 compared to the best competitor.

AB - Knowledge graph (KG) has been fully considered in natural language generation (NLG) tasks. A KG can help models generate controllable text and achieve better performance. However, most existing related approaches still lack explainability and scalability in large-scale knowledge reasoning. In this work, we propose a novel CogNLG framework for KG-to-text generation tasks. Our CogNLG is implemented based on the dual-process theory in cognitive science. It consists of two systems: one system acts as the analytic system for knowledge extraction, and another is the perceptual system for text generation by using existing knowledge. During text generation, CogNLG provides a visible and explainable reasoning path. Our framework shows excellent performance on all datasets and achieves a BLEU score of 36.7, which increases by 6.7 compared to the best competitor.

KW - KG-to-text

KW - cognitive graph

KW - natural language generation

UR - https://onlinelibrary.wiley.com/doi/10.1111/exsy.13461

UR - http://www.scopus.com/inward/record.url?scp=85173729667&partnerID=8YFLogxK

U2 - 10.1111/exsy.13461

DO - 10.1111/exsy.13461

M3 - Article

SN - 0266-4720

VL - 41

JO - Expert Systems

JF - Expert Systems

IS - 1

M1 - e13461

ER -

CogNLG: Cognitive Graph for KG-to-text Generation

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this