WebFormer: The Web-page Transformer for Structure Information Extraction
This work addresses structure information extraction for web document understanding, offering a novel method to handle diverse web layouts, though it is incremental in improving existing transformer-based approaches.
The paper tackles the problem of extracting structured text fields from web pages by introducing WebFormer, a transformer model that incorporates web layout information through HTML tokens and attention patterns, achieving superior performance on SWDE and Common Crawl benchmarks.
Structure information extraction refers to the task of extracting structured text fields from web pages, such as extracting a product offer from a shopping page including product title, description, brand and price. It is an important research topic which has been widely studied in document understanding and web search. Recent natural language models with sequence modeling have demonstrated state-of-the-art performance on web information extraction. However, effectively serializing tokens from unstructured web pages is challenging in practice due to a variety of web layout patterns. Limited work has focused on modeling the web layout for extracting the text fields. In this paper, we introduce WebFormer, a Web-page transFormer model for structure information extraction from web documents. First, we design HTML tokens for each DOM node in the HTML by embedding representations from their neighboring tokens through graph attention. Second, we construct rich attention patterns between HTML tokens and text tokens, which leverages the web layout for effective attention weight computation. We conduct an extensive set of experiments on SWDE and Common Crawl benchmarks. Experimental results demonstrate the superior performance of the proposed approach over several state-of-the-art methods.