Home > Research > Publications & Outputs > Are rule-based approaches a thing of the past?

Research

Electronic data

  • SEPLN_Anaphora-6

    Accepted author manuscript, 215 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

View graph of relations

Are rule-based approaches a thing of the past?: The case of anaphora resolution

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Forthcoming
<mark>Journal publication date</mark>17/05/2024
<mark>Journal</mark>Procesamiento del Lenguaje Natural
Issue number2
Volume72
Publication StatusAccepted/In press
<mark>Original language</mark>English

Abstract

In this paper, we evaluate and compare new variants of a popular rulebased
anaphora resolution algorithm with the original version. We seek to establish
whether configurations that benefit from Deep Learning, LLMs and eye-tracking
data (always) outperform the original rule-based algorithm. The results of this study
suggest that while algorithms based in Deep Learning and LLMs usually perform
better than rule-based ones, this is not always the case, and we argue that rule-based approaches still have a place in today’s research.