Non-neural Models Matter: A Re-evaluation of Neural Referring Expression Generation Systems

Fahime Same, Guanyi Chen, Kees van Deemter

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Abstract

    In recent years, neural models have often outperformed rule-based and classic Machine Learning approaches in NLG. These classic approaches are now often disregarded, for example when new neural models are evaluated. We argue that they should not be overlooked, since, for some tasks, well-designed non-neural approaches achieve better performance than neural ones. In this paper, the task of generating referring expressions in linguistic context is used as an example. We examined two very different English datasets (WEBNLG and WSJ), and evaluated each algorithm using both automatic and human evaluations. Overall, the results of these evaluations suggest that rule-based systems with simple rule sets achieve on-par or better performance on both datasets compared to state-of-the-art neural REG systems. In the case of the more realistic dataset, WSJ, a machine learning-based system with well-designed linguistic features performed best. We hope that our work can encourage researchers to consider non-neural models in future.
    Original languageEnglish
    Title of host publicationProceedings of ACL 2022
    PublisherAssociation for Computational Linguistics
    Pages5554–5567
    DOIs
    Publication statusPublished - May 2022

    Fingerprint

    Dive into the research topics of 'Non-neural Models Matter: A Re-evaluation of Neural Referring Expression Generation Systems'. Together they form a unique fingerprint.

    Cite this