Cross-Domain Web Information Extraction at Pinterest
This work addresses the challenge of converting unstructured web information into structured formats for enhancing user experiences and content distribution at Pinterest, representing an incremental improvement with specific gains in efficiency and cost.
The paper tackles the problem of extracting structured product data from e-commerce websites by developing a system that combines structural, visual, and text modalities into a compact webpage representation, enabling simple models like XGBoost to achieve high accuracy and scalability, processing over 1,000 URLs per second while being 1000 times more cost-effective than GPT alternatives.
The internet offers a massive repository of unstructured information, but it's a significant challenge to convert this into a structured format. At Pinterest, the ability to accurately extract structured product data from e-commerce websites is essential to enhance user experiences and improve content distribution. In this paper, we present Pinterest's system for attribute extraction, which achieves remarkable accuracy and scalability at a manageable cost. Our approach leverages a novel webpage representation that combines structural, visual, and text modalities into a compact form, optimizing it for small model learning. This representation captures each visible HTML node with its text, style and layout information. We show how this allows simple models such as eXtreme Gradient Boosting (XGBoost) to extract attributes more accurately than much more complex Large Language Models (LLMs) such as Generative Pre-trained Transformer (GPT). Our results demonstrate a system that is highly scalable, processing over 1,000 URLs per second, while being 1000 times more cost-effective than the cheapest GPT alternatives.