Neural data-to-text generation: An encoder-decoder structure with Multi-Candidate-based Context Module

Jing Ming Guo; Koksheik Wong; Bo Ruei Cheng; Chen Hung Chung

doi:10.1109/ISPACS57703.2022.10082828

Neural data-to-text generation: An encoder-decoder structure with Multi-Candidate-based Context Module

Jing Ming Guo, Koksheik Wong, Bo Ruei Cheng, Chen Hung Chung

Malaysia Sch of Information Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research

1 Citation (Scopus)

Abstract

The data-to-text generation task mainly uses the encoder-decoder architecture, in which the context module provides the information that the decoder wants to observe at the moment. However, there are multiple entities and elements in a single sentence. We conjecture that the architecture has room for improvement to be more suitable for the data-to-text generation task. This paper proposes the Multi-Candidate-based Context Module, using the concept of multiple candidates to simultaneously observe multiple entities and their records. The experiment confirms the effectiveness of our multi-candidate concept and the improvement over the state-of-the-art on the recently released Rotowire dataset.

Original language	English
Title of host publication	2022 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2022
Editors	Hitoshi Kiya
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Number of pages	4
ISBN (Electronic)	9798350332421
ISBN (Print)	9798350332438
DOIs	https://doi.org/10.1109/ISPACS57703.2022.10082828
Publication status	Published - 2022
Event	IEEE International Symposium on Intelligent Signal Processing and Communications Systems (ISPACS) 2022 - Penang, Malaysia Duration: 22 Nov 2022 → 25 Nov 2022 https://ieeexplore.ieee.org/xpl/conhome/10082768/proceeding (Proceedings) https://web.archive.org/web/20220925073530/https://www.ispacs2022.org/committee.html (Website)

Conference

Conference	IEEE International Symposium on Intelligent Signal Processing and Communications Systems (ISPACS) 2022
Abbreviated title	ISPACS 2022
Country/Territory	Malaysia
City	Penang
Period	22/11/22 → 25/11/22
Internet address	https://ieeexplore.ieee.org/xpl/conhome/10082768/proceeding (Proceedings) https://web.archive.org/web/20220925073530/https://www.ispacs2022.org/committee.html (Website)

Keywords

Data-to-Text Generation
Multi-Candidate-based Mechanism
Natural Language Generation
Supervised Learning

Access to Document

10.1109/ISPACS57703.2022.10082828

Cite this

Guo, J. M., Wong, K., Cheng, B. R., & Chung, C. H. (2022). Neural data-to-text generation: An encoder-decoder structure with Multi-Candidate-based Context Module. In H. Kiya (Ed.), 2022 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2022 IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISPACS57703.2022.10082828

Guo, Jing Ming ; Wong, Koksheik ; Cheng, Bo Ruei et al. / Neural data-to-text generation : An encoder-decoder structure with Multi-Candidate-based Context Module. 2022 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2022. editor / Hitoshi Kiya. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2022.

@inproceedings{32a2515058e8491eafea7a11d2b011cd,

title = "Neural data-to-text generation: An encoder-decoder structure with Multi-Candidate-based Context Module",

abstract = "The data-to-text generation task mainly uses the encoder-decoder architecture, in which the context module provides the information that the decoder wants to observe at the moment. However, there are multiple entities and elements in a single sentence. We conjecture that the architecture has room for improvement to be more suitable for the data-to-text generation task. This paper proposes the Multi-Candidate-based Context Module, using the concept of multiple candidates to simultaneously observe multiple entities and their records. The experiment confirms the effectiveness of our multi-candidate concept and the improvement over the state-of-the-art on the recently released Rotowire dataset.",

keywords = "Data-to-Text Generation, Multi-Candidate-based Mechanism, Natural Language Generation, Supervised Learning",

author = "Guo, {Jing Ming} and Koksheik Wong and Cheng, {Bo Ruei} and Chung, {Chen Hung}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; IEEE International Symposium on Intelligent Signal Processing and Communications Systems (ISPACS) 2022, ISPACS 2022 ; Conference date: 22-11-2022 Through 25-11-2022",

year = "2022",

doi = "10.1109/ISPACS57703.2022.10082828",

language = "English",

isbn = "9798350332438",

editor = "Hitoshi Kiya",

booktitle = "2022 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2022",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

url = "https://ieeexplore.ieee.org/xpl/conhome/10082768/proceeding, https://web.archive.org/web/20220925073530/https://www.ispacs2022.org/committee.html",

}

Guo, JM, Wong, K, Cheng, BR & Chung, CH 2022, Neural data-to-text generation: An encoder-decoder structure with Multi-Candidate-based Context Module. in H Kiya (ed.), 2022 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2022. IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, IEEE International Symposium on Intelligent Signal Processing and Communications Systems (ISPACS) 2022, Penang, Malaysia, 22/11/22. https://doi.org/10.1109/ISPACS57703.2022.10082828

Neural data-to-text generation: An encoder-decoder structure with Multi-Candidate-based Context Module. / Guo, Jing Ming; Wong, Koksheik; Cheng, Bo Ruei et al.
2022 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2022. ed. / Hitoshi Kiya. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2022.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research

TY - GEN

T1 - Neural data-to-text generation

T2 - IEEE International Symposium on Intelligent Signal Processing and Communications Systems (ISPACS) 2022

AU - Guo, Jing Ming

AU - Wong, Koksheik

AU - Cheng, Bo Ruei

AU - Chung, Chen Hung

PY - 2022

Y1 - 2022

N2 - The data-to-text generation task mainly uses the encoder-decoder architecture, in which the context module provides the information that the decoder wants to observe at the moment. However, there are multiple entities and elements in a single sentence. We conjecture that the architecture has room for improvement to be more suitable for the data-to-text generation task. This paper proposes the Multi-Candidate-based Context Module, using the concept of multiple candidates to simultaneously observe multiple entities and their records. The experiment confirms the effectiveness of our multi-candidate concept and the improvement over the state-of-the-art on the recently released Rotowire dataset.

AB - The data-to-text generation task mainly uses the encoder-decoder architecture, in which the context module provides the information that the decoder wants to observe at the moment. However, there are multiple entities and elements in a single sentence. We conjecture that the architecture has room for improvement to be more suitable for the data-to-text generation task. This paper proposes the Multi-Candidate-based Context Module, using the concept of multiple candidates to simultaneously observe multiple entities and their records. The experiment confirms the effectiveness of our multi-candidate concept and the improvement over the state-of-the-art on the recently released Rotowire dataset.

KW - Data-to-Text Generation

KW - Multi-Candidate-based Mechanism

KW - Natural Language Generation

KW - Supervised Learning

UR - http://www.scopus.com/inward/record.url?scp=85152297718&partnerID=8YFLogxK

U2 - 10.1109/ISPACS57703.2022.10082828

DO - 10.1109/ISPACS57703.2022.10082828

M3 - Conference Paper

AN - SCOPUS:85152297718

SN - 9798350332438

BT - 2022 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2022

A2 - Kiya, Hitoshi

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

Y2 - 22 November 2022 through 25 November 2022

ER -

Guo JM, Wong K, Cheng BR, Chung CH. Neural data-to-text generation: An encoder-decoder structure with Multi-Candidate-based Context Module. In Kiya H, editor, 2022 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2022. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2022 doi: 10.1109/ISPACS57703.2022.10082828

Neural data-to-text generation: An encoder-decoder structure with Multi-Candidate-based Context Module

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this