Vorschau! Die Detailseite für diese Publikation wurde nicht aktiviert!
PromptIE - Information Extraction with Prompt-Engineering and Large Language Models
Abstract
Extracting triples of subjects, objects, and predicates from text to populate knowledge bases traditionally involves several intermediate steps such as co-reference resolution, named entity recognition, and relationship extraction. Treating triple extraction as translation task from source sentences to sets of triples, we present an end-to-end solution for information extraction that uses task prefixes to prompts a fine-tuned large language model to extract triples from text. Thus, the need for data labeling and training multiple models is reduced.
Mehr zum Titel
| Titel | PromptIE - Information Extraction with Prompt-Engineering and Large Language Models |
|---|---|
| Medien | In: Stephanidis, C., Antona, M., Ntoa, S., Salvendy, G. (eds) HCI International 2023 Posters. HCII 2023. Communications in Computer and Information Science, Springer, Cham |
| Verlag | Stephanidis, C., Antona, M., Ntoa, S., Salvendy, G. (eds); Springer, Cham |
| Herausgeber | HCI International 2023 Posters |
| Band | 1836 |
| ISBN | 978-3-031-36003-9 |
| Verfasser | Prof. Dr. Sigurd Schacht, Sudarshan Kamath Barkur, Carsten Lanquillon |
| Seiten | 507–514 |
| Veröffentlichungsdatum | 09.07.2023 |
| Projekttitel | DIAS |
| Zitation | Schacht, Sigurd; Kamath Barkur, Sudarshan; Lanquillon, Carsten (2023): PromptIE - Information Extraction with Prompt-Engineering and Large Language Models. In: Stephanidis, C., Antona, M., Ntoa, S., Salvendy, G. (eds) HCI International 2023 Posters. HCII 2023. Communications in Computer and Information Science, Springer, Cham 1836, 507–514. DOI: 10.1007/978-3-031-36004-6_69 |