PuerAI at SemEval-2026 Task 5: Homograph Appropriateness Assessment via DeBERTa Contrastive Regression and Contextual Grouping

AbstractTo assess homograph appropriateness in narrative contexts for SemEval-2026 Task 5, we propose a contrastive regression framework. This approach combines candidate sense definitions with full narrative texts to establish an MSE regression baseline, further enhanced by a contextual grouping ranking loss that models relative rationality among senses. Evaluated on the official AmbiStory dataset, our method consistently outperforms the baseline in accuracy and Spearman correlation. These results validate the efficacy of relative order modeling for capturing fine-grained semantic nuances in complex narratives. The code is available at: https://github.com/daojiaxu/Semeval2026task5.