Extend item-polysemy modeling with context-aware dual tokenization

Extend DSRec’s basic item-polysemous modeling by developing context-aware dual-tokenization that incorporates item-side semantic roles, potentially using a Variational Autoencoder.

Background

DSRec represents each item through separate long-term and short-term interest embeddings to model context-dependent item semantics. The authors characterize this polysemous modeling as novel but basic and explicitly identify extending it with context-aware dual-tokenization and item-side semantic roles as an unresolved direction for future research.

References

While DSRec achieves advanced performance, several limitations remain open for future research. First, the item polysemous modeling is novel but basic, we plan to extend by context aware dual-tokenization to incorporate item-side semantic roles, such as Variational AutoEncoder (VAE).

— Dual-Interest Sequential Product Recommendation With Multi-Granular SSM  (2609.21548 - Liao et al., 18 Sep 2026) in Conclusion and Future Work, subsection “Future Work”