Knowledge Graph-Enhanced Neural Query Rewriting

The main task of an e-commerce search engine is to semantically match the user query to the product inventory and retrieve the most relevant items that match the user's intent. This task is not trivial as often there can be a mismatch between the user's intent and the product inventory for various reasons, the most prevalent being: (i) the buyers and sellers use different vocabularies, which leads to a mismatch; (ii) the inventory doesn't contain products that match the user's intent. To build a successful e-commerce platform it is of paramount importance to be able to address both of these challenges. To do so, query rewriting approaches are used, which try to bridge the semantic gap between the user's intent and the available product inventory. Such approaches use a combination of query token dropping, replacement and expansion. In this work we introduce a novel Knowledge Graph-enhanced neural query rewriting in the e-commerce domain. We use a relationship-rich product Knowledge Graph to infuse auxiliary knowledge in a transformer-based query rewriting deep neural network. Experiments on two tasks, query pruning and complete query rewriting, show that our proposed approach significantly outperforms a baseline BERT-based query rewriting solution.