🌌 Sparse Encoder Playground
Explore different SPLADE models and their sparse representation types, and calculate similarity between query and document representations.
Produce a Sparse Representation of an Input Text
Calculate Dot Product Similarity Between Encoded Query and Document
References
This demo utilizes SPLADE models. For more details, please refer to the following papers:
Formal, T., Lassance, C., Piwowarski, B., & Clinchant, S. (2022). From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective. arXiv preprint arXiv:2205.04733. Available at: https://arxiv.org/abs/2205.04733
Lassance, C., Déjean, H., Formal, T., & Clinchant, S. (2024). SPLADE-v3: New baselines for SPLADE. arXiv preprint arXiv:2403.06789. Available at: https://arxiv.org/abs/2403.06789