Sparse lexical representation learning has demonstrated much progress in improving passage retrieval effectiveness in recent models such as DeepImpact, uniCOIL, and SPLADE. This paper describes a straightforward yet effective approach for sparsifying lexical representations for passage retrieval, building on SPLADE by introducing a top-k masking scheme to control sparsity and a self-learning method to coax masked representations to mimic unmasked representations. A basic implementation of our model is competitive with more sophisticated approaches and achieves a good balance between effectiveness and efficiency. The simplicity of our methods opens the door for future explorations in lexical representation learning for passage retrieval.
@article{arxiv.2112.09628,
title = {Sparsifying Sparse Representations for Passage Retrieval by Top-$k$ Masking},
author = {Jheng-Hong Yang and Xueguang Ma and Jimmy Lin},
journal= {arXiv preprint arXiv:2112.09628},
year = {2021}
}