Reproduce “SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hui Zhou, Jian Hui Ji, Lei Ma, Rong Xiao, Xiaoyi Zeng
SAM-D2Q adds relevant, image-supported query terms to e-commerce product records before Boolean indexing, filtering out title-covered terms and training visual attributes through counterfactual masking. It also scores new terms for relevance and commercial value. At Top-3000, it raises relevant retrieved items 30.7% over original-title retrieval. In a live test, the full module lifted GMV 3.38% and Pay Count 2.27% on active products.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.