Salvato in:
Dettagli Bibliografici
Autori principali: Zavarella, Vanni, Gamero-Salinas, Juan Carlos, Consoli, Sergio
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2408.02377
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911207831633920
author Zavarella, Vanni
Gamero-Salinas, Juan Carlos
Consoli, Sergio
author_facet Zavarella, Vanni
Gamero-Salinas, Juan Carlos
Consoli, Sergio
contents Knowledge graphs (KGs) have been successfully applied to the analysis of complex scientific and technological domains, with automatic KG generation methods typically building upon relation extraction models capturing fine-grained relations between domain entities in text. While these relations are fully applicable across scientific areas, existing models are trained on few domain-specific datasets such as SciERC and do not perform well on new target domains. In this paper, we experiment with leveraging in-context learning capabilities of Large Language Models to perform schema-constrained data annotation, collecting in-domain training instances for a Transformer-based relation extraction model deployed on titles and abstracts of research papers in the Architecture, Construction, Engineering and Operations (AECO) domain. By assessing the performance gain with respect to a baseline Deep Learning architecture trained on off-domain data, we show that by using a few-shot learning strategy with structured prompts and only minimal expert annotation the presented approach can potentially support domain adaptation of a science KG generation model.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02377
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Few-Shot Approach for Relation Extraction Domain Adaptation using Large Language Models
Zavarella, Vanni
Gamero-Salinas, Juan Carlos
Consoli, Sergio
Computation and Language
Artificial Intelligence
Knowledge graphs (KGs) have been successfully applied to the analysis of complex scientific and technological domains, with automatic KG generation methods typically building upon relation extraction models capturing fine-grained relations between domain entities in text. While these relations are fully applicable across scientific areas, existing models are trained on few domain-specific datasets such as SciERC and do not perform well on new target domains. In this paper, we experiment with leveraging in-context learning capabilities of Large Language Models to perform schema-constrained data annotation, collecting in-domain training instances for a Transformer-based relation extraction model deployed on titles and abstracts of research papers in the Architecture, Construction, Engineering and Operations (AECO) domain. By assessing the performance gain with respect to a baseline Deep Learning architecture trained on off-domain data, we show that by using a few-shot learning strategy with structured prompts and only minimal expert annotation the presented approach can potentially support domain adaptation of a science KG generation model.
title A Few-Shot Approach for Relation Extraction Domain Adaptation using Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2408.02377