EUVIMEDEUVIMED entdecken
Crossref

LlamATE

Hanh Thi-Hong Tran, Carlos-Emiliano González-Gallardo, Antoine Doucet, Senja Pollak

Terminology. International Journal of Theoretical and Applied Issues in Specialized Communication · 23.05.2025 · 31 (1) · 5-36

DOI: 10.1075/term.00082.tra ↗

Kurz gefasst

Fachartikel in der Zeitschrift Terminology. International Journal of Theoretical and Applied Issues in Specialized Communication, online erschienen am 23.05.2025. Verfasst von Hanh Thi-Hong Tran und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 57 Literaturangaben.

AbstractBibliografische AngabenZitieren

Abstract (Originalsprache)

Over the past decades, automatic term or terminology extraction (ATE), a natural language processing (NLP) task that aims to identify terms from specific domains by providing a list of candidate terms, has been challenging due to the strong influence of domain-specific differences on term definitions. Leveraging the advances of large-scale language models (LLMs), we propose LlamATE , a framework to verify the impact of domain specificity on ATE when using in-context learning prompts in open-sourced LLM-based chat models, namely Llama-2-Chat . We evaluate how well the LLM-based chat (e.g., using reinforcement learning with human feedback (RLHF)) models perform with different levels of domain-related information in the dominant language in NLP research (e.g., English) and other European languages (e.g., French, Slovene) from ACTER datasets, i.e., in-domain and cross-domain demonstrations with and without domain enunciation. Furthermore, we examine the potential of cross-lingual and cross-domain prompting to reduce the need for extensive data annotation of the target domain and language. The results demonstrate the potential of implicit in-domain learning where examples of the target domain are used as demonstrations for the prompts without specifying the domain of each example, and cross-lingual learning when knowledge is transferred from the dominant to lesser-represented European languages as for the data used to pre-train the LLMs. LlamATE also offers a valuable compromise by reducing the need for extensive data annotation, making it suitable for real-world applications where labeled corpora are scarce. The source code is publicly available at the following link: https://github.com/honghanhh/terminology2024 .

Zitieren

APA

Tran, H. T., González-Gallardo, C., Doucet, A., & Pollak, S. (2025). LlamATE. Terminology. International Journal of Theoretical and Applied Issues in Specialized Communication, 31(1), 5-36. https://doi.org/10.1075/term.00082.tra

Vancouver

Tran HT, González-Gallardo C, Doucet A, Pollak S. LlamATE. Terminology. International Journal of Theoretical and Applied Issues in Specialized Communication. 2025;31(1):5-36. doi:10.1075/term.00082.tra

BibTeX
@article{Tran2025,
  author = {Tran, Hanh Thi-Hong and González-Gallardo, Carlos-Emiliano and Doucet, Antoine and Pollak, Senja},
  title = {LlamATE},
  journal = {Terminology. International Journal of Theoretical and Applied Issues in Specialized Communication},
  year = {2025},
  volume = {31},
  number = {1},
  pages = {5--36},
  doi = {10.1075/term.00082.tra}
}
Infokarte | EUVIMED

Artikeldaten derzeit nicht verfügbar.

Recherche