EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Extensive Benchmark of Frugal Encoder–Decoder Language Models for Datatype Properties Extraction and RDF Knowledge Graph Generation

Célian Ringwald, Fabien Gandon, Catherine Faron, Franck Michel, Hanna Abi Akl

Semantic Web: – Interoperability, Usability, Applicability · 2026-07 · 17 (4)

DOI: 10.1177/22104968261452987 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Semantic Web: – Interoperability, Usability, Applicability, online erschienen am 03.06.2026. Verfasst von Célian Ringwald und 4 weiteren Autor:innen. Die Arbeit nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The choice made for representing the inputs and outputs of generative pretrained language models (PLMs) can impact their fine-tuning on a new task. This article focuses on the fine-tuning and linearization process to generate facts extracted from text. On a restricted relation extraction (RE) task, we challenged five encoder–decoder models, including BART, T5, CodeT5, FlanT5, and PileT5 by fine-tuning them on 13 linearization variations, including RDF standard syntaxes and variations thereof. Our benchmark covers the validity of the produced triples, the model’s performance, the training behavior, and the resources needed. We show these PLMs can learn some syntaxes more easily than others, and we identify a promising “Turtle Light” syntax supporting the quick and robust learning of the RE task.

Zitieren

APA

Ringwald, C., Gandon, F., Faron, C., Michel, F., & Akl, H. A. (2026). Extensive Benchmark of Frugal Encoder–Decoder Language Models for Datatype Properties Extraction and RDF Knowledge Graph Generation. Semantic Web: – Interoperability, Usability, Applicability, 17(4). https://doi.org/10.1177/22104968261452987

Vancouver

Ringwald C, Gandon F, Faron C, Michel F, Akl HA. Extensive Benchmark of Frugal Encoder–Decoder Language Models for Datatype Properties Extraction and RDF Knowledge Graph Generation. Semantic Web: – Interoperability, Usability, Applicability. 2026;17(4). doi:10.1177/22104968261452987

BibTeX
@article{Ringwald2026,
  author = {Ringwald, Célian and Gandon, Fabien and Faron, Catherine and Michel, Franck and Akl, Hanna Abi},
  title = {Extensive Benchmark of Frugal Encoder–Decoder Language Models for Datatype Properties Extraction and RDF Knowledge Graph Generation},
  journal = {Semantic Web: – Interoperability, Usability, Applicability},
  year = {2026},
  volume = {17},
  number = {4},
  doi = {10.1177/22104968261452987}
}
Kostenlos starten →