Purpose <p>Recognizing previously unseen classes with neural networks is a significant challenge due to their limited generalization capabilities. This issue is particularly critical in safety-critical domains such as medical applications, where accurate classification is essential for reliability and patient safety. Zero-shot learning methods address this challenge by utilizing additional semantic data, with their performance relying heavily on the quality of the generated embeddings.</p> Methods <p>This work investigates the use of full descriptive sentences, generated by a Sentence-BERT model, as class representations, compared to simpler category-based word embeddings derived from a BERT model. Additionally, the impact of z-score normalization as a post-processing step on these embeddings is explored. The proposed approach is evaluated on a multi-label generalized zero-shot learning task, focusing on the recognition of surgical instruments in endoscopic images from minimally invasive cholecystectomies.</p> Results <p>The results demonstrate that combining sentence embeddings and z-score normalization significantly improves model performance. For unseen classes, the AUROC improves from 43.9&#xa0;% to 64.9&#xa0;%, and the multi-label accuracy from 26.1&#xa0;% to 79.5&#xa0;%. Overall performance measured across both seen and unseen classes improves from 49.3&#xa0;% to 64.9&#xa0;% in AUROC and from 37.3&#xa0;% to 65.1&#xa0;% in multi-label accuracy, highlighting the effectiveness of our approach.</p> Conclusion <p>These findings demonstrate that sentence embeddings and z-score normalization can substantially enhance the generalization performance of zero-shot learning models. However, as the study is based on a single dataset, future work should validate the method across diverse datasets and application domains to establish its robustness and broader applicability.</p>