A case-based approach to data-to-text generation.

Upadhyay, Ashish; Massie, Stewart; Singh, Ritwik Kumar; Gupta, Garima; Ojha, Muneendra

Abstract

Traditional Data-to-Text Generation (D2T) systems utilise carefully crafted domain specific rules and templates to generate high quality accurate texts. More recent approaches use neural systems to learn domain rules from the training data to produce very fluent and diverse texts. However, there is a trade-off with rule-based systems producing accurate text but that may lack variation, while learning-based systems produce more diverse texts but often with poorer accuracy. In this paper, we propose a Case-Based approach for D2T that mitigates the impact of this trade-off by dynamically selecting templates from the training corpora. In our approach we develop a novel case-alignment based, feature weighing method that is used to build an effective similarity measure. Extensive experimentation is performed on a sports domain dataset. Through Extractive Evaluation metrics, we demonstrate the benefit of the CBR system over a rule-based baseline and a neural benchmark.

Citation

UPADHYAY, A., MASSIE, S., SINGH, R.K., GUPTA, G. and OJHA, M. 2021. A case-based approach to data-to-text generation. In Sánchez-Ruiz, A.A. and Floyd, M.W. (eds.) Case-based reasoning research and development: proceedings of 29th International conference case-based reasoning 2021 (ICCBR 2021), 13-16 September 2021, Salamanca, Spain. Lecture notes in computer science (LNCS), 12877. Cham: Springer [online], pages 232-247. Available from: https://doi.org/10.1007/978-3-030-86957-1_16

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 29th International conference on case-based reasoning 2021 (ICCBR 2021)
• Start Date: Sep 13, 2021
• End Date: Sep 16, 2021
• Acceptance Date: Jun 11, 2021
• Online Publication Date: Sep 10, 2021
• Publication Date: Dec 31, 2021
• Deposit Date: Oct 26, 2021
• Publicly Available Date: Oct 26, 2021
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Pages: 232-247
• Series Title: Lecture notes in computer science (LNCS)
• Series Number: 12877
• Series ISSN: 0302-9743
• Book Title: Case-based reasoning research and development
• ISBN: 9783030869564
• DOI: https://doi.org/10.1007/978-3-030-86957-1_16
• Keywords: Data-to-text; Textual case-based reasoning (Textual CBR); Feature weighting
• Public URL: https://rgu-repository.worktribe.com/output/1482039
• Related Public URLs: https://rgu-repository.worktribe.com/output/1512837