A Few-Shot Approach for Relation Extraction Domain Adaptation using Large Language Models
This work addresses the challenge of adapting relation extraction models to new scientific domains like AECO, offering an incremental improvement over existing methods.
The paper tackles the problem of poor performance of relation extraction models on new scientific domains by using a few-shot learning strategy with large language models to generate in-domain training data, showing potential for domain adaptation in knowledge graph generation.
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.