IntelliExtract - Solution Variants

IntelliExtract understands and removes unwanted text like advertisements and navigational text. It is designed to give the user control over the output through two extraction solutions:

• Text Extraction Solution - is designed to extract text from a webpage or similar web pages across multiple websites and provide a clean output ready for further processing (e.g. analysis, summarization, report writing). It can be trained to comprehend different "information types" e.g. news articles, product pages, reviews, blogs, postings from multiple forums.
• Entity Extraction and Classification Solution - is designed to extract specific "information pieces" termed as entities of text from a webpage, analyze, associate and classify the same under various categories and output info in predefined categories like Person Name, Role, Organization, Location, Email ID, Telephone & Fax nos. It can be trained to classify user defined entities e.g. names of technologies, chemicals and alike.