DeepGen: Diverse Search Ad Generation and Real-Time Customization

TL;DR

DeepGen is a scalable system that automatically generates and customizes diverse, fluent search ads in real-time using advanced NLG models, improving relevance and diversity for BingAds.

Contribution

The paper introduces DeepGen, a novel system combining diverse, controllable NLG and real-time customization for search ads, addressing factuality, speed, and diversity challenges.

Findings

System serves approximately 4% of Bing's global ads.

Generated ads show increased diversity and relevance.

System effectively balances diversity and inference speed.

Abstract

We present DeepGen, a system deployed at web scale for automatically creating sponsored search advertisements (ads) for BingAds customers. We leverage state-of-the-art natural language generation (NLG) models to generate fluent ads from advertiser's web pages in an abstractive fashion and solve practical issues such as factuality and inference speed. In addition, our system creates a customized ad in real-time in response to the user's search query, therefore highlighting different aspects of the same product based on what the user is looking for. To achieve this, our system generates a diverse choice of smaller pieces of the ad ahead of time and, at query time, selects the most relevant ones to be stitched into a complete ad. We improve generation diversity by training a controllable NLG model to generate multiple ads for the same web page highlighting different selling points. Our system design further improves diversity horizontally by first running an ensemble of generation models trained with different objectives and then using a diversity sampling algorithm to pick a diverse subset of generation results for online selection. Experimental results show the effectiveness of our proposed system design. Our system is currently deployed in production, serving ${\sim}4\%$ of global ads served in Bing.