enunlg: a Python library for reproducible neural data-to-text experimentation

Howcroft, David M; Gkatzia, Dimitra

Abstract

Over the past decade, a variety of neural ar-chitectures for data-to-text generation (NLG) have been proposed. However, each system typically has its own approach to pre-and post-processing and other implementation details. Diversity in implementations is desirable, but it also confounds attempts to compare model performance: are the differences due to the proposed architectures or are they a byprod-uct of the libraries used or a result of pre-and post-processing decisions made? To improve reproducibility, we re-implement several pre-Transformer neural models for data-to-text NLG within a single framework to facilitate direct comparisons of the models themselves and better understand the contributions of other design choices. We release our library at https: //github.com/NapierNLP/enunlg to serve as a baseline for ongoing work in this area including research on NLG for low-resource languages where transformers might not be optimal .

Citation

Howcroft, D. M., & Gkatzia, D. (2023, September). enunlg: a Python library for reproducible neural data-to-text experimentation. Presented at 16th International Natural Language Generation Conference, Prague, Czechia

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 16th International Natural Language Generation Conference
• Start Date: Sep 13, 2023
• End Date: Sep 15, 2023
• Acceptance Date: Jul 12, 2023
• Online Publication Date: Sep 11, 2023
• Publication Date: 2023
• Deposit Date: Nov 15, 2023
• Publicly Available Date: Nov 15, 2023
• Publisher: Association for Computational Linguistics (ACL)
• Pages: 4-5
• Book Title: Proceedings of the 16th International Natural Language Generation Conference: System Demonstrations
• ISBN: 979-8-89176-002-8
• Public URL: http://researchrepository.napier.ac.uk/Output/3385911
• Publisher URL: https://aclanthology.org/2023.inlg-demos.2/