# FreeDOM: A Transferable Neural Architecture for Structured Information Extraction on Web Documents

arXiv: https://arxiv.org/abs/2010.10755 · HTML: https://mlsanity.com/paper/2010.10755/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2020.

## Built on by (most cited first, 22 of 22)

- [NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search](https://mlsanity.com/paper/2105.14444/) (2021)
- [MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding](https://mlsanity.com/paper/2110.08518/) (2021)
- [WebFormer: The Web-page Transformer for Structure Information Extraction](https://mlsanity.com/paper/2202.00217/) (2022)
- [Schema-Driven Information Extraction from Heterogeneous Tables](https://mlsanity.com/paper/2305.14336/) (2023)
- [DOM-LM: Learning Generalizable Representations for HTML Documents](https://mlsanity.com/paper/2201.10608/) (2022)
- [AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation](https://mlsanity.com/paper/2404.12753/) (2024)
- [Simplified DOM Trees for Transferable Attribute Extraction from the Web](https://mlsanity.com/paper/2101.02415/) (2021)
- [CoVA: Context-aware Visual Attention for Webpage Information Extraction](https://mlsanity.com/paper/2110.12320/) (2021)
- [Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding](https://mlsanity.com/paper/2402.18262/) (2024)
- [PLAtE: A Large-scale Dataset for List Page Web Extraction](https://mlsanity.com/paper/2205.12386/) (2022)
- [The Klarna Product Page Dataset: Web Element Nomination with Graph Neural Networks and Large Language Models](https://mlsanity.com/paper/2111.02168/) (2021)
- [XPath Agent: An Efficient XPath Programming Agent Based on LLM for Web Crawler](https://mlsanity.com/paper/2502.15688/) (2024)
- [Towards Zero-shot Relation Extraction in Web Mining: A Multimodal Approach with Relative XML Path](https://mlsanity.com/paper/2305.13805/) (2023)
- [Hypertext Entity Extraction in Webpage](https://mlsanity.com/paper/2403.01698/) (2024)
- [Label-Efficient Self-Training for Attribute Extraction from Semi-Structured Web Documents](https://mlsanity.com/paper/2208.13086/) (2022)
- [AutoFAIR : Automatic Data FAIRification via Machine Reading](https://mlsanity.com/paper/2408.04673/) (2024)
- [Author Unknown: Evaluating Performance of Author Extraction Libraries on Global Online News Articles](https://mlsanity.com/paper/2410.19771/) (2024)
- [Knowledge Bases in Support of Large Language Models for Processing Web News](https://mlsanity.com/paper/2411.08278/) (2024)
- [LiveWeb-IE: A Benchmark For Online Web Information Extraction](https://mlsanity.com/paper/2603.13773/) (2026)
- [Co-Scraper: query-aware DOM Pruning and Reusable Scraper Synthesis for Lightweight Web Data Extraction](https://mlsanity.com/paper/2606.14821/) (2026)
- [news-crawler-LM: A Small Long-Context Model For High-Quality News Crawling](https://mlsanity.com/paper/2607.21284/) (2026)
- [Visual-Aware Representation of Web Pages for Machine Learning Applications](https://mlsanity.com/paper/2608.18727/) (2026)

## Abstract (arXiv)

Extracting structured data from HTML documents is a long-studied problem with a broad range of applications like augmenting knowledge bases, supporting faceted search, and providing domain-specific experiences for key verticals like shopping and movies. Previous approaches have either required a small number of examples for each target site or relied on carefully handcrafted heuristics built over visual renderings of websites. In this paper, we present a novel two-stage neural approach, named FreeDOM, which overcomes both these limitations. The first stage learns a representation for each DOM node in the page by combining both the text and markup information. The second stage captures longer range distance and semantic relatedness using a relational neural network. By combining these stages, FreeDOM is able to generalize to unseen sites after training on a small number of seed sites from that vertical without requiring expensive hand-crafted features over visual renderings of the page. Through experiments on a public dataset with 8 different verticals, we show that FreeDOM beats the previous state of the art by nearly 3.7 F1 points on average without requiring features over rendered pages or expensive hand-crafted features.