EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Phoenixes at LLMs4OL 2024 Tasks A, B, and C: Retrieval Augmented Generation for Ontology Learning

Mahsa Sanaei, Fatemeh Azizi, Hamed Babaei Giglou

Open Conference Proceedings · 02.10.2024 · 4 · 39-47

DOI: 10.52825/ocp.v4i.2482 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Open Conference Proceedings, online erschienen am 02.10.2024. Verfasst von Mahsa Sanaei und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) showed great capabilities in ontology learning (OL) where they automatically extract knowledge from text. In this paper, we proposed a Retrieval Augmented Generation (RAG) formulation for three different tasks of ontology learning defined in the LLMs4OL Challenge at ISWC 2024. For task A - term typing - we considered terms as a query and encoded the query through the Query Encoder model for searching through knowledge base embedding of types embeddings obtained through Context Encoder. Next, using Zero-Shot Prompt template we asked LLM to determine what types are appropriate for a given term within the term typing task. Similarly, for Task B, we calculated the similarity matrix using an encoder-based transformer model, and by applying the similarity threshold we considered only similar pairs to query LLM to identify whatever pairs have the "is-a" relation between a given type and in a case of having the relationships which one is "parent" and which one is "child". In final, for Task C -- non-taxonomic relationship extraction -- we combined both approaches for Task A and B, where first using Task B formulation, child-parents are identified then using Task A, we assigned them an appropriate relationship. For the LLMs4OL challenge, we experimented with the proposed framework over 5 subtasks of Task A, all subtasks of Task B, and one subtask of Task C using Mistral-7B LLM.

Zitieren

APA

Sanaei, M., Azizi, F., & Giglou, H. B. (2024). Phoenixes at LLMs4OL 2024 Tasks A, B, and C: Retrieval Augmented Generation for Ontology Learning. Open Conference Proceedings, 4, 39-47. https://doi.org/10.52825/ocp.v4i.2482

Vancouver

Sanaei M, Azizi F, Giglou HB. Phoenixes at LLMs4OL 2024 Tasks A, B, and C: Retrieval Augmented Generation for Ontology Learning. Open Conference Proceedings. 2024;4:39-47. doi:10.52825/ocp.v4i.2482

BibTeX
@article{Sanaei2024,
  author = {Sanaei, Mahsa and Azizi, Fatemeh and Giglou, Hamed Babaei},
  title = {Phoenixes at LLMs4OL 2024 Tasks A, B, and C: Retrieval Augmented Generation for Ontology Learning},
  journal = {Open Conference Proceedings},
  year = {2024},
  volume = {4},
  pages = {39--47},
  doi = {10.52825/ocp.v4i.2482}
}
Kostenlos starten →