Extraction

Rosoka Extraction is a multilingual NLP, API-driven engine that performs entity and relationship extraction along with an integrated geotagging capability. Rosoka Extraction allows a user access to the Java API or REST web service. Results are output in XML, JSON, or POJO. Users must have their own, separate data store to persist results. Rosoka Extraction ships with the Core Rosoka LxBase; however, a different LxBase can be deployed with this product. Rosoka Toolkit is needed to modify or enhance the Core Rosoka LxBase. The intended Rosoka Extraction user is a tech savvy user familiar with API integration programming who wants to plug extraction in to their production pipeline. This is also an appropriate product for OEM integration. Rosoka Extraction provides the basic workflow for processing documents. It provides document retrieval, automatic routing based on licenses, tokenization, rule checking, output formatting, and many other utilities.