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

Standard

Are rule-based approaches a thing of the past? The case of anaphora resolution. / Mitkov, Ruslan; Ha, Le An.
In: Procesamiento del Lenguaje Natural, Vol. 72, No. 2, 17.05.2024.

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

Harvard

Mitkov, R & Ha, LA 2024, 'Are rule-based approaches a thing of the past? The case of anaphora resolution', Procesamiento del Lenguaje Natural, vol. 72, no. 2.

APA

Mitkov, R., & Ha, L. A. (in press). Are rule-based approaches a thing of the past? The case of anaphora resolution. Procesamiento del Lenguaje Natural, 72(2).

Vancouver

Mitkov R, Ha LA. Are rule-based approaches a thing of the past? The case of anaphora resolution. Procesamiento del Lenguaje Natural. 2024 May 17;72(2).

Author

Mitkov, Ruslan ; Ha, Le An. / Are rule-based approaches a thing of the past? The case of anaphora resolution. In: Procesamiento del Lenguaje Natural. 2024 ; Vol. 72, No. 2.

Bibtex

@article{e89e618f4ff84e80ac04ee0c0e189ede,
title = "Are rule-based approaches a thing of the past?: The case of anaphora resolution",
abstract = "In this paper, we evaluate and compare new variants of a popular rulebasedanaphora resolution algorithm with the original version. We seek to establishwhether configurations that benefit from Deep Learning, LLMs and eye-trackingdata (always) outperform the original rule-based algorithm. The results of this studysuggest that while algorithms based in Deep Learning and LLMs usually performbetter than rule-based ones, this is not always the case, and we argue that rule-based approaches still have a place in today{\textquoteright}s research.",
author = "Ruslan Mitkov and Ha, {Le An}",
year = "2024",
month = may,
day = "17",
language = "English",
volume = "72",
journal = "Procesamiento del Lenguaje Natural",
number = "2",

}

RIS

TY - JOUR

T1 - Are rule-based approaches a thing of the past?

T2 - The case of anaphora resolution

AU - Mitkov, Ruslan

AU - Ha, Le An

PY - 2024/5/17

Y1 - 2024/5/17

N2 - In this paper, we evaluate and compare new variants of a popular rulebasedanaphora resolution algorithm with the original version. We seek to establishwhether configurations that benefit from Deep Learning, LLMs and eye-trackingdata (always) outperform the original rule-based algorithm. The results of this studysuggest that while algorithms based in Deep Learning and LLMs usually performbetter 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.

AB - In this paper, we evaluate and compare new variants of a popular rulebasedanaphora resolution algorithm with the original version. We seek to establishwhether configurations that benefit from Deep Learning, LLMs and eye-trackingdata (always) outperform the original rule-based algorithm. The results of this studysuggest that while algorithms based in Deep Learning and LLMs usually performbetter 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.

M3 - Journal article

VL - 72

JO - Procesamiento del Lenguaje Natural

JF - Procesamiento del Lenguaje Natural

IS - 2

ER -