Graph-based Multilingual Product Retrieval in E-commerce Search
It addresses the need for efficient and scalable multilingual retrieval systems in global e-commerce platforms to reduce costs and facilitate expansion, though it is incremental as it builds on existing transformer and graph neural network methods.
The paper tackles the problem of multilingual product retrieval in e-commerce search by proposing a universal end-to-end system using a multilingual graph attention network, which outperforms state-of-the-art baselines by 35% recall and 25% mAP on average and shows significant increases in conversion/revenue in online experiments.
Nowadays, with many e-commerce platforms conducting global business, e-commerce search systems are required to handle product retrieval under multilingual scenarios. Moreover, comparing with maintaining per-country specific e-commerce search systems, having a universal system across countries can further reduce the operational and computational costs, and facilitate business expansion to new countries. In this paper, we introduce a universal end-to-end multilingual retrieval system, and discuss our learnings and technical details when training and deploying the system to serve billion-scale product retrieval for e-commerce search. In particular, we propose a multilingual graph attention based retrieval network by leveraging recent advances in transformer-based multilingual language models and graph neural network architectures to capture the interactions between search queries and items in e-commerce search. Offline experiments on five countries data show that our algorithm outperforms the state-of-the-art baselines by 35% recall and 25% mAP on average. Moreover, the proposed model shows significant increase of conversion/revenue in online A/B experiments and has been deployed in production for multiple countries.