EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

U-DepPLLaMA: Universal Dependency Parsing via Auto-regressive Large Language Models

Claudiu Daniel Hromei, Danilo Croce, Roberto Basili

Italian Journal of Computational Linguistics · 2024 · 10 (1)

DOI: 10.4000/125nm ↗

Kurz gefasst

Fachartikel in der Zeitschrift Italian Journal of Computational Linguistics, 2024. Verfasst von Claudiu Daniel Hromei und 2 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper investigates the rapidly advancing domain of Large Language Models (LLMs) and their growing potential in various fields. A central focus is the exploration of LLMs, e.g., LLaMA, as powerful tools for modeling and representing linguistic information, especially in the realm of syntax. We aim to evaluate the ability of these models to encode syntactic information, especially when explicitly supplied, through fine-tuning processes. Traditionally, Dependency Parsing has relied on specific techniques and dedicated architectures. Our research shifts this approach, conceptualizing it as a sequence-to-sequence task where Language Models interpret and transform syntax into bracketed structures that reflect dependency graphs. We introduce U-DepPLLaMA (Universal Dependency Parsing via auto-regressive LLMs based on LLaMA), a novel architecture optimized for multilingual, end-to-end Dependency Parsing. Our experimental evaluation, across 50 datasets in 26 languages from the Universal Dependency Treebank, shows that LLMs can be effectively trained for dependency parsing without the need for task-specific architectures. The results are on par with current state-of-the-art methods and demonstrate resilience across varying sentence complexities and lengths.

Zitieren

APA

Hromei, C. D., Croce, D., & Basili, R. (2024). U-DepPLLaMA: Universal Dependency Parsing via Auto-regressive Large Language Models. Italian Journal of Computational Linguistics, 10(1). https://doi.org/10.4000/125nm

Vancouver

Hromei CD, Croce D, Basili R. U-DepPLLaMA: Universal Dependency Parsing via Auto-regressive Large Language Models. Italian Journal of Computational Linguistics. 2024;10(1). doi:10.4000/125nm

BibTeX
@article{Hromei2024,
  author = {Hromei, Claudiu Daniel and Croce, Danilo and Basili, Roberto},
  title = {U-DepPLLaMA: Universal Dependency Parsing via Auto-regressive Large Language Models},
  journal = {Italian Journal of Computational Linguistics},
  year = {2024},
  volume = {10},
  number = {1},
  doi = {10.4000/125nm}
}
Kostenlos starten →