ASHISH UPADHYAY a.upadhyay@rgu.ac.uk
Research Student
CBR assisted context-aware surface realisation for data-to-text generation.
Upadhyay, Ashish; Massie, Stewart
Authors
Dr Stewart Massie s.massie@rgu.ac.uk
Associate Professor
Abstract
Current state-of-the-art neural systems for Data-to-Text Generation (D2T) struggle to generate content from past events with interesting insights. This is because these systems have limited access to historic data and can also hallucinate inaccurate facts in their generations. In this paper, we propose a CBR-assisted context-aware methodology for surface realisation in D2T that carefully selects important contextual data from past events and utilises a hybrid CBR and neural text generator to generate the final event summary. Through extensive experimentation on a sports domain dataset, we empirically demonstrate that our proposed method is able to accurately generate contextual content closer to human-authored summaries when compared to other state-of-the-art systems.
Citation
UPADHYAY, A. and MASSIE, S. 2023. CBR assisted context-aware surface realisation for data-to-text generation. In MASSIE, S. and CHAKRABORTI, S. (eds.) 2023. Case-based reasoning research and development: proceedings of the 31st International conference on case-based reasoning 2023, (ICCBR 2023), 17-20 July 2023, Aberdeen, UK. Lecture notes in computer science (LNCS), 14141. Cham: Springer [online], pages 34-49. Available from: https://doi.org/10.1007/978-3-031-40177-0_3
Conference Name | 31st International conference on case-based reasoning 2023 (ICCBR 2023): CBR in a data-driven world |
---|---|
Conference Location | Aberdeen, UK |
Start Date | Jul 17, 2023 |
End Date | Jul 20, 2023 |
Acceptance Date | Jun 16, 2023 |
Online Publication Date | Jul 17, 2023 |
Publication Date | Jul 30, 2023 |
Deposit Date | Jul 21, 2023 |
Publicly Available Date | Jul 18, 2024 |
Publisher | Springer |
Pages | 34-49 |
Series Title | Lecture notes in computer science (LNCS) |
Series Number | 14141 |
Series ISSN | 0302-9743; 1611-3349 |
Book Title | Case-based reasoning research and development: proceedings of 31st International conference on case-based reasoning 2023 (ICCBR 2023): CBR in a data-driven world |
ISBN | 9783031401763 |
DOI | https://doi.org/10.1007/978-3-031-40177-0_3 |
Keywords | Textual case-based reasoning; Data-to-text generation; Content selection; Surface realisation |
Public URL | https://rgu-repository.worktribe.com/output/2015590 |
Files
This file is under embargo until Jul 18, 2024 due to copyright reasons.
Contact publications@rgu.ac.uk to request a copy for personal use.
You might also like
Content type profiling of data-to-text generation datasets.
(2022)
Conference Proceeding
A case-based approach for content planning in data-to-text generation.
(2022)
Conference Proceeding
A case-based approach to data-to-text generation.
(2021)
Conference Proceeding
Case-based approach to automated natural language generation for obituaries.
(2020)
Conference Proceeding
WEC: weighted ensemble of text classifiers.
(2020)
Conference Proceeding
Downloadable Citations
About OpenAIR@RGU
Administrator e-mail: publications@rgu.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search