Query Brand Entity Linking in E-Commerce Search
This addresses the problem of accurately linking brands in e-commerce search queries for users and platforms, representing an incremental improvement with specific domain applications.
The paper tackled the brand entity linking problem for e-commerce search queries, which are short and unstructured, by developing a two-stage approach and a novel end-to-end solution using extreme multi-class classification, achieving validation through offline benchmarks and online A/B tests.
In this work, we address the brand entity linking problem for e-commerce search queries. The entity linking task is done by either i)a two-stage process consisting of entity mention detection followed by entity disambiguation or ii) an end-to-end linking approaches that directly fetch the target entity given the input text. The task presents unique challenges: queries are extremely short (averaging 2.4 words), lack natural language structure, and must handle a massive space of unique brands. We present a two-stage approach combining named-entity recognition with matching, and a novel end-to-end solution using extreme multi-class classification. We validate our solutions by both offline benchmarks and the impact of online A/B test.