Efficient Information Extraction in Few-Shot Relation Classification through Contrastive Representation Learning

arXiv:2403.16543v1 Announce Type: new
Abstract: Differentiating relationships between entity pairs with limited labeled instances poses a significant challenge in few-shot relation classification. Representations of textual data extract rich information spanning the domain, entities, and relations. In this paper, we introduce a novel approach to enhance information extraction combining multiple sentence representations and contrastive learning. While representations in relation classification are commonly extracted using entity marker tokens, we argue that substantial information within the internal model representations remains untapped. To address …

abstract arxiv challenge classification cs.ai cs.cl data domain extract extraction few-shot information information extraction instances multiple novel paper relations relationships representation representation learning textual through type