Future Direction

The following is a list of areas that we hope to expand Baleen into over the coming years. Any contributions in these areas are very welcome.

• Improved entity extraction
• Relationship extraction
• Event extraction
• Entity disambiguation (within the same document, and across multiple documents)
• Exploitation of structure within documents (including tables, headers, paragraphs, etc.)
• Document summarisation and triage
• Knowledge representation and persistence
• Scalability
• Measurement and evaluation of performance