IBM’s new OCR provides higher character accuracy and detection recall giving you greater extraction of key insights from documents in sub-optimal conditions such as irregular fonts, insufficient resolution, bad lighting from mobile capture and even variety of colors and backgrounds. 

Traditional enterprise search engines perform keyword searches and provide end-users with links to documentation. But with Watson Discovery, you move beyond keyword search to navigate confidently through your documents using faceted search to find the relevant information needed. The design of this platform ensures that the information you need is easily accessible and can push to downstream automation via JSON output. 

The platform’s out-of-the-box NLP enrichments include entity extraction, sentiment analysis, emotion analysis, keyword extractions, category classification, concept tagging and more. 

IBM Watson Discovery uses foundation models from Watson Natural Language Processing (NLP) for advanced processing and understanding of text, enabling the accurate extraction of information and insights from business documents, accelerating processes and generating insights. 

Define custom entity types and annotate entity mentions to iteratively train a supervised entity recognition model with active learning techniques to accelerate training.