Cross-Domain Web Information Extraction at Pinterest

• URL: http://arxiv.org/abs/2508.01096v1
• Date: Fri, 01 Aug 2025 22:22:35 GMT
• Title: Cross-Domain Web Information Extraction at Pinterest
• Authors: Michael Farag, Patrick Halina, Andrey Zaytsev, Alekhya Munagala, Imtihan Ahmed, Junhao Wang,
• Abstract summary: We present Pinterest's system for attribute extraction, which achieves remarkable accuracy and scalability at a manageable cost.<n>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)<n>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.
• Score: 1.7702475609045947
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• (PASS) Visual Prompt Locates Good Structure Sparsity through a Recurrent HyperNetwork [60.889175951038496]
  Large-scale neural networks have demonstrated remarkable performance in different domains like vision and language processing. One of the key questions of structural pruning is how to estimate the channel significance. We propose a novel algorithmic framework, namely textttPASS. It is a tailored hyper-network to take both visual prompts and network weight statistics as input, and output layer-wise channel sparsity in a recurrent manner.
  arXiv  Detail & Related papers  (2024-07-24T16:47:45Z)
• Hypertext Entity Extraction in Webpage [112.56734676713721]
  We introduce a textbfMoE-based textbfEntity textbfExtraction textbfFramework (textitMoEEF), which integrates multiple features to enhance model performance. We also analyze the effectiveness of hypertext features in textitHEED and several model components in textitMoEEF.
  arXiv  Detail & Related papers  (2024-03-04T03:21:40Z)
• Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search [60.626459715780605]
  Given a descriptive text query, text-based person search aims to retrieve the best-matched target person from an image gallery. Such a cross-modal retrieval task is quite challenging due to significant modality gap, fine-grained differences and insufficiency of annotated data. In this paper, we propose a simple yet effective dual Transformer model for text-based person search.
  arXiv  Detail & Related papers  (2023-11-15T16:26:49Z)
• Enhancing Visually-Rich Document Understanding via Layout Structure Modeling [91.07963806829237]
  We propose GraphLM, a novel document understanding model that injects layout knowledge into the model. We evaluate our model on various benchmarks, including FUNSD, XFUND and CORD, and achieve state-of-the-art results.
  arXiv  Detail & Related papers  (2023-08-15T13:53:52Z)
• Large Scale Generative Multimodal Attribute Extraction for E-commerce Attributes [23.105116746332506]
  E-commerce websites (e.g. Amazon) have a plethora of structured and unstructured information (text and images) present on the product pages. Sellers often either don't label or mislabel values of the attributes (e.g. color, size etc.) for their products. We present a scalable solution for this problem using textbfMXT, consisting of three key components.
  arXiv  Detail & Related papers  (2023-06-01T06:21:45Z)
• WebFormer: The Web-page Transformer for Structure Information Extraction [44.46531405460861]
  Structure information extraction refers to the task of extracting structured text fields from web pages. Recent natural language models with sequence modeling have demonstrated state-of-the-art performance on web information extraction. We introduce WebFormer, a Web-page transFormer model for structure information extraction from web documents.
  arXiv  Detail & Related papers  (2022-02-01T04:44:02Z)
• The Klarna Product Page Dataset: Web Element Nomination with Graph Neural Networks and Large Language Models [51.39011092347136]
  We introduce the Klarna Product Page dataset, a collection of webpages that surpasses existing datasets in richness and variety. We empirically benchmark a range of Graph Neural Networks (GNNs) on the web element nomination task. Second, we introduce a training refinement procedure that involves identifying a small number of relevant elements from each page. Third, we introduce the Challenge Nomination Training Procedure, a novel training approach that further boosts nomination accuracy.
  arXiv  Detail & Related papers  (2021-11-03T12:13:52Z)
• Simplified DOM Trees for Transferable Attribute Extraction from the Web [15.728164692696689]
  Given a web page, extracting a structured object along with various attributes of interest can facilitate a variety of downstream applications. Existing approaches formulate the problem as a DOM tree node tagging task. We propose a novel transferable method, SimpDOM, to tackle the problem by efficiently retrieving useful context for each node.
  arXiv  Detail & Related papers  (2021-01-07T07:41:55Z)
• ZeroShotCeres: Zero-Shot Relation Extraction from Semi-Structured Webpages [66.45377533562417]
  We propose a solution for "zero-shot" open-domain relation extraction from webpages with a previously unseen template. Our model uses a graph neural network-based approach to build a rich representation of text fields on a webpage.
  arXiv  Detail & Related papers  (2020-05-14T16:15:58Z)
• Boilerplate Removal using a Neural Sequence Labeling Model [4.056234173482691]
  We propose a neural sequence labeling model that does not rely on any hand-crafted features but takes only the HTML tags and words that appear in a web page as input. This allows us to present a browser extension which highlights the content of arbitrary web pages directly within the browser using our model.
  arXiv  Detail & Related papers  (2020-04-22T08:06:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.