Guardado en:
Detalles Bibliográficos
Autores principales: Bazin, Guillaume, Tannier, Xavier, Adda, Fanny, Cohen, Ariel, Redjdal, Akram, Kempf, Emmanuelle
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2506.13177
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915346437373952
author Bazin, Guillaume
Tannier, Xavier
Adda, Fanny
Cohen, Ariel
Redjdal, Akram
Kempf, Emmanuelle
author_facet Bazin, Guillaume
Tannier, Xavier
Adda, Fanny
Cohen, Ariel
Redjdal, Akram
Kempf, Emmanuelle
contents Rules could be an information extraction (IE) default option, compared to ML and LLMs in terms of sustainability, transferability, interpretability, and development burden. We suggest a sustainable and combined use of rules and ML as an IE method. Our approach starts with an exhaustive expert manual highlighting in a single working session of a representative subset of the data corpus. We developed and validated the feasibility and the performance metrics of the REST decision tool to help the annotator choose between rules as a by default option and ML for each entity of an IE task. REST makes the annotator visualize the characteristics of each entity formalization in the free texts and the expected rule development feasibility and IE performance metrics. ML is considered as a backup IE option and manual annotation for training is therefore minimized. The external validity of REST on a 12-entity use case showed good reproducibility.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13177
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Development of the user-friendly decision aid Rule-based Evaluation and Support Tool (REST) for optimizing the resources of an information extraction task
Bazin, Guillaume
Tannier, Xavier
Adda, Fanny
Cohen, Ariel
Redjdal, Akram
Kempf, Emmanuelle
Computation and Language
Rules could be an information extraction (IE) default option, compared to ML and LLMs in terms of sustainability, transferability, interpretability, and development burden. We suggest a sustainable and combined use of rules and ML as an IE method. Our approach starts with an exhaustive expert manual highlighting in a single working session of a representative subset of the data corpus. We developed and validated the feasibility and the performance metrics of the REST decision tool to help the annotator choose between rules as a by default option and ML for each entity of an IE task. REST makes the annotator visualize the characteristics of each entity formalization in the free texts and the expected rule development feasibility and IE performance metrics. ML is considered as a backup IE option and manual annotation for training is therefore minimized. The external validity of REST on a 12-entity use case showed good reproducibility.
title Development of the user-friendly decision aid Rule-based Evaluation and Support Tool (REST) for optimizing the resources of an information extraction task
topic Computation and Language
url https://arxiv.org/abs/2506.13177