SETU's suite of products help organizations semantify their content very quickly and provide it in RDF standard formats that can be understood by semantic search eng ines of the future. These tools would also help organizations reap the early benefits of semantic web to improve information access and efficiency.
Information Extraction
SETU's Information Extraction Engine helps generate structured, unambiguous information which is ready for machine processing, from unstructured, ambiguous text written in human language. The Extraction Engine accomplishes the tasks of automatic template filling and automatic concept and event identification and the associated details that can be found in any given text.
Summarization
Setu's Ssummarizer can be used to summarize both single file documets or multiple file documents. The Summarizer can input multiple files in ZIP format and summarize the documents. It also provides options for summariztion to be Query Focused or Query Independent. See Summarizer product page for more details and links to live demo.
Enterprise Document Search
Setu Software's Enterprise search engine provides intelligent contextual search capabilities for your enterprise intranets. With this engine you will have the ability to define and index multiple document collections. The search engine is built with performance in mind, resulting in sub-second retrieval times and highly scalable to hundreds of millions of documents. Our engine is capable of handling multiple languages along with English.
Local Language Search
SETU offers local language search engines for many world languages. Currently two systems are deployed. SETU's Indian language search engine is deployed at http://ilsearch.rediff.com. Setooz currently services 23 world languages as a pilot. The languages cover most of the languages spoken in Scandinavian, Eastern and Central European and Middle Eastern countries.
Data Resources
SETU has built many local language resources over a period of time. These resources may be useful in many of your internal projects. For example, we offer local language vocabulary with the frequency of their occurrences in a sufficiently large corpus. We also offer term n-gram model of a given language.