A Concept Knowledge-Driven Keywords Retrieval Framework for Sponsored Search

TL;DR

This paper introduces a knowledge-driven framework for retrieving synonymous keywords in sponsored search, leveraging concept tagging and conceptual patterns to improve accuracy and generalization, especially for long-tail instances.

Contribution

The paper proposes a novel conceptual retrieval framework that enhances synonym matching in sponsored search by integrating concept knowledge, addressing limitations of data-driven deep learning methods.

Findings

Significant revenue improvement in Baidu's sponsored search system

Effective in handling long-tail instances with shared conceptual patterns

Outperforms existing methods in offline and online experiments

Abstract

In sponsored search, retrieving synonymous keywords for exact match type is important for accurately targeted advertising. Data-driven deep learning-based method has been proposed to tackle this problem. An apparent disadvantage of this method is its poor generalization performance on entity-level long-tail instances, even though they might share similar concept-level patterns with frequent instances. With the help of a large knowledge base, we find that most commercial synonymous query-keyword pairs can be abstracted into meaningful conceptual patterns through concept tagging. Based on this fact, we propose a novel knowledge-driven conceptual retrieval framework to mitigate this problem, which consists of three parts: data conceptualization, matching via conceptual patterns and concept-augmented discrimination. Both offline and online experiments show that our method is very effective. This framework has been successfully applied to Baidu's sponsored search system, which yields a significant improvement in revenue.