Info Station Content Classifier categorizes unstructured information by performing Knowledge graph-powered semantic analysis over the full text of the documents and applying supervised machine learning and rules that automate classification decisions.
A Multi-class Text Classification Approach
Info Station Content Classification provides context-sensitive analysis and automation features to organize unstructured content. The solution categorizes unstructured information by analyzing the full text of documents and Webpages and applying rules that automate classification decisions. It can organize information by policies or key words, and it can assign metadata that is based on, for example, the full context of a document. The solution works with Info Station Sell-side Platform to gather training data.
In this demo, we are excited to be sharing our hard-earned insights on building an industry leading classifier. We show you how we trained a model to make educated guesses of higher probability thresholds and classify miscellaneous articles into their respective categories- automatically, in a fraction of the time it would take to perform this manually, and error-free.
Paste any document or article below
Represented as a knowledge graph that contains factual information: diverse data about rich set of entities and concepts of interest. Possessing enough lexical and grammatical knowledge to comprehend text, combined with the skill to resolve ambiguity and extract relationships from free text.
Classify documents by common entities or 55+ general categories such as News, Technology and Entertainment. Build relationship graphs of entities extracted from news or wikipedia articles, by using signals from the state of the art syntax analysis.