Entity Disambiguation via Fusion Entity Decoding

arXiv:2404.01626v1 Announce Type: new
Abstract: Entity disambiguation (ED), which links the mentions of ambiguous entities to their referent entities in a knowledge base, serves as a core component in entity linking (EL). Existing generative approaches demonstrate improved accuracy compared to classification approaches under the standardized ZELDA benchmark. Nevertheless, generative approaches suffer from the need for large-scale pre-training and inefficient generation. Most importantly, entity descriptions, which could contain crucial information to distinguish similar entities from each other, are often overlooked. We …

abstract accuracy arxiv benchmark classification core cs.cl cs.ir decoding fusion generative knowledge knowledge base type via