Webstruct

Webstruct is a library for creating statistical NER systems that work on HTML data, i.e. a library for building tools that extract named entities (addresses, organization names, open hours, etc) from webpages.

Contents:

• Webstruct
  • Overview
  • Installation
• Tutorial
  • Get annotated data
  • From HTML to Tokens
  • Feature Extraction
  • Using a Sequence Labelling Toolkit
  • Named Entity Recognition
  • Entity Grouping
  • Model Development
• Reference
  • HTML Loaders
  • Feature Extraction
  • Model Creation Helpers
  • Metrics
  • Entity Grouping
  • Wapiti Helpers
  • CRFsuite Helpers
  • WebAnnotator Utilities
  • BaseSequenceClassifier
  • Miscellaneous

Indices and tables

• Index
• Module Index
• Search Page