Unified Generative & Dense Retrieval for Query Rewriting in Sponsored Search

TL;DR

This paper introduces CLOVER-Unity, a unified model combining generative and dense retrieval methods for query rewriting in sponsored search, leading to improved relevance, efficiency, and revenue in large-scale online experiments.

Contribution

The paper proposes CLOVER-Unity, a novel unified model that integrates generative and dense retrieval approaches, outperforming individual models and reducing computational costs.

Findings

CLOVER-Unity outperforms individual NLG and DR models on benchmarks.

Achieves 9.8% higher good keyword density.

Online experiments show 0.89% increase in clicks and 1.27% revenue growth.

Abstract

Sponsored search is a key revenue source for search engines, where advertisers bid on keywords to target users or search queries of interest. However, finding relevant keywords for a given query is challenging due to the large and dynamic keyword space, ambiguous user/advertiser intents, and diverse possible topics and languages. In this work, we present a comprehensive comparison between two paradigms for online query rewriting: Generative (NLG) and Dense Retrieval (DR) methods. We observe that both methods offer complementary benefits that are additive. As a result, we show that around 40% of the high-quality keywords retrieved by the two approaches are unique and not retrieved by the other. To leverage the strengths of both methods, we propose CLOVER-Unity, a novel approach that unifies generative and dense retrieval methods in one single model. Through offline experiments, we show that the NLG and DR components of CLOVER-Unity consistently outperform individually trained NLG and DR models on public and internal benchmarks. Furthermore, we show that CLOVER-Unity achieves 9.8% higher good keyword density than the ensemble of two separate DR and NLG models while reducing computational costs by almost half. We conduct extensive online A/B experiments on Microsoft Bing in 140+ countries and achieve improved user engagement, with an average increase in total clicks by 0.89% and increased revenue by 1.27%. We also share our practical lessons and optimization tricks for deploying such unified models in production.