DSTI at LLMs4OL 2024 Task A: Intrinsic versus extrinsic knowledge for type classification
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929474629533696 |
|---|---|
| author | Akl, Hanna Abi |
| author_facet | Akl, Hanna Abi |
| contents | We introduce semantic towers, an extrinsic knowledge representation method, and compare it to intrinsic knowledge in large language models for ontology learning. Our experiments show a trade-off between performance and semantic grounding for extrinsic knowledge compared to a fine-tuned model intrinsic knowledge. We report our findings on the Large Language Models for Ontology Learning (LLMs4OL) 2024 challenge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_14236 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DSTI at LLMs4OL 2024 Task A: Intrinsic versus extrinsic knowledge for type classification Akl, Hanna Abi Computation and Language Artificial Intelligence Machine Learning We introduce semantic towers, an extrinsic knowledge representation method, and compare it to intrinsic knowledge in large language models for ontology learning. Our experiments show a trade-off between performance and semantic grounding for extrinsic knowledge compared to a fine-tuned model intrinsic knowledge. We report our findings on the Large Language Models for Ontology Learning (LLMs4OL) 2024 challenge. |
| title | DSTI at LLMs4OL 2024 Task A: Intrinsic versus extrinsic knowledge for type classification |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2408.14236 |