Web2Text: Deep Structured Boilerplate Removal
This addresses the need for efficient boilerplate removal in web-based NLP and information retrieval tasks, representing an incremental improvement over existing methods.
The authors tackled the problem of extracting main content from web pages by introducing a model that classifies text blocks as boilerplate or content using a hidden Markov model on CNN-derived DOM features, achieving new state-of-the-art performance on the CleanEval benchmark and improving retrieval on ClueWeb12.
Web pages are a valuable source of information for many natural language processing and information retrieval tasks. Extracting the main content from those documents is essential for the performance of derived applications. To address this issue, we introduce a novel model that performs sequence labeling to collectively classify all text blocks in an HTML page as either boilerplate or main content. Our method uses a hidden Markov model on top of potentials derived from DOM tree features using convolutional neural networks. The proposed method sets a new state-of-the-art performance for boilerplate removal on the CleanEval benchmark. As a component of information retrieval pipelines, it improves retrieval performance on the ClueWeb12 collection.