EUVIMEDEUVIMED entdecken
Crossref

What’s in a Name? Evaluating Assembly-Part Semantic Knowledge in Language Models Through User-Provided Names in Computer Aided Design Files

Peter Meltzer, Joseph G. Lambourne, Daniele Grandi

Journal of Computing and Information Science in Engineering · 01.01.2024 · 24 (1)

DOI: 10.1115/1.4062454 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computing and Information Science in Engineering, online erschienen am 23.06.2023. Verfasst von Peter Meltzer und 2 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: Autodesk.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic knowledge of part-part and part-whole relationships in assemblies is useful for a variety of tasks from searching design repositories to the construction of engineering knowledge bases. In this work, we propose that the natural language names designers use in computer aided design (CAD) software are a valuable source of such knowledge, and that large language models (LLMs) contain useful domain-specific information for working with this data as well as other CAD and engineering-related tasks. In particular, we extract and clean a large corpus of natural language part, feature, and document names and use this to quantitatively demonstrate that a pre-trained language model can outperform numerous benchmarks on three self-supervised tasks, without ever having seen this data before. Moreover, we show that fine-tuning on the text data corpus further boosts the performance on all tasks, thus demonstrating the value of the text data which until now has been largely ignored. We also identify key limitations to using LLMs with text data alone, and our findings provide a strong motivation for further work into multi-modal text-geometry models. To aid and encourage further work in this area we make all our data and code publicly available.

Förderung

  • Autodesk

Zitieren

APA

Meltzer, P., Lambourne, J. G., & Grandi, D. (2024). What’s in a Name? Evaluating Assembly-Part Semantic Knowledge in Language Models Through User-Provided Names in Computer Aided Design Files. Journal of Computing and Information Science in Engineering, 24(1). https://doi.org/10.1115/1.4062454

Vancouver

Meltzer P, Lambourne JG, Grandi D. What’s in a Name? Evaluating Assembly-Part Semantic Knowledge in Language Models Through User-Provided Names in Computer Aided Design Files. Journal of Computing and Information Science in Engineering. 2024;24(1). doi:10.1115/1.4062454

BibTeX
@article{Meltzer2024,
  author = {Meltzer, Peter and Lambourne, Joseph G. and Grandi, Daniele},
  title = {What’s in a Name? Evaluating Assembly-Part Semantic Knowledge in Language Models Through User-Provided Names in Computer Aided Design Files},
  journal = {Journal of Computing and Information Science in Engineering},
  year = {2024},
  volume = {24},
  number = {1},
  doi = {10.1115/1.4062454}
}
Kostenlos starten →