CoSiNES: Contrastive Siamese Network for Entity Standardization
This addresses the problem of mapping noisy entity mentions to standard entities in knowledge bases, especially in cross-domain scenarios with scarce labeled data, representing an incremental improvement over previous context-heavy or domain-specific methods.
The authors tackled entity standardization for noisy mentions in free-form text by proposing CoSiNES, a framework using a contrastive Siamese network with a pretrained language model, achieving higher accuracy and faster runtime than baselines on a new technology dataset and competitive performance across four other domains.
Entity standardization maps noisy mentions from free-form text to standard entities in a knowledge base. The unique challenge of this task relative to other entity-related tasks is the lack of surrounding context and numerous variations in the surface form of the mentions, especially when it comes to generalization across domains where labeled data is scarce. Previous research mostly focuses on developing models either heavily relying on context, or dedicated solely to a specific domain. In contrast, we propose CoSiNES, a generic and adaptable framework with Contrastive Siamese Network for Entity Standardization that effectively adapts a pretrained language model to capture the syntax and semantics of the entities in a new domain. We construct a new dataset in the technology domain, which contains 640 technical stack entities and 6,412 mentions collected from industrial content management systems. We demonstrate that CoSiNES yields higher accuracy and faster runtime than baselines derived from leading methods in this domain. CoSiNES also achieves competitive performance in four standard datasets from the chemistry, medicine, and biomedical domains, demonstrating its cross-domain applicability.