Recently, semantic search has been successfully applied to e-commerce product search and the learned semantic space(s) for query and product encoding are expected to generalize to unseen queries or products. Yet, whether generalization can conveniently emerge has not been thoroughly studied in the domain thus far. In this paper, we examine several general-domain and domain-specific pre-trained Roberta variants and discover that general-domain fine-tuning does not help generalization, which aligns with the discovery of prior art. Proper domain-specific fine-tuning with clickstream data can lead to better model generalization, based on a bucketed analysis of a publicly available manual annotated query-product pair da
Cite
@article{arxiv.2204.05231,
title = {Towards Generalizable Semantic Product Search by Text Similarity Pre-training on Search Click Logs},
author = {Zheng Liu and Wei Zhang and Yan Chen and Weiyi Sun and Tianchuan Du and Benjamin Schroeder},
journal= {arXiv preprint arXiv:2204.05231},
year = {2022}
}