Triangular Bidword Generation for Sponsored Search Auction

TL;DR

This paper introduces TRIDENT, a triangular bidword generation model that leverages high-quality <query, advertisement> pairs to generate relevant bidwords, improving over noisy data-based methods in sponsored search auctions.

Contribution

The paper proposes a novel triangular training framework that jointly learns to generate bidwords from search queries and advertisements using high-quality paired data.

Findings

TRIDENT outperforms existing methods in relevance and diversity of bidwords.

Experimental results show improved bidword quality in automatic and human evaluations.

Online data validation confirms effectiveness in real-world product search.

Abstract

Sponsored search auction is a crucial component of modern search engines. It requires a set of candidate bidwords that advertisers can place bids on. Existing methods generate bidwords from search queries or advertisement content. However, they suffer from the data noise in <query, bidword> and <advertisement, bidword> pairs. In this paper, we propose a triangular bidword generation model (TRIDENT), which takes the high-quality data of paired <query, advertisement> as a supervision signal to indirectly guide the bidword generation process. Our proposed model is simple yet effective: by using bidword as the bridge between search query and advertisement, the generation of search query, advertisement and bidword can be jointly learned in the triangular training framework. This alleviates the problem that the training data of bidword may be noisy. Experimental results, including automatic and human evaluations, show that our proposed TRIDENT can generate relevant and diverse bidwords for both search queries and advertisements. Our evaluation on online real data validates the effectiveness of the TRIDENT's generated bidwords for product search.