home
The Increasing Demand for Knowledge Management /Discovery Applications
Web-based technologies have led to the availability of vast and increasing amounts of information. Much of this information is unstructured, making it difficult for users to access the information they need to make decisions. This lack of structure is particularly relevant to research and discovery professionals and similar users.
At data intensive organizations, the answers one is seeking are rarely found in a single document. More often than not, elements of multiple documents must be combined to provide the answers. Most search engines and retrieval methods are simply not capable of handling this. Their methods range from information retrieval of a single item, like a document or an article, to slightly advanced retrieval of related articles and even the authors who created them.
The Collexis Difference
The superior Collexis approach is known as high definition search and knowledge discovery.
Collexis makes significant improvements to standard data and information retrieval capabilities by discovering the relationships between the elements of different content sources and uncovering unique information. Additionally, Collexis can look at aggregate information from multiple content sources to create potentially new hypotheses based on large volumes of unstructured content.
What makes Collexis unique?
Initially, Collexis differentiates itself from full-text search engines by using thesauri for information retrieval. The high-quality search is based on semantics that have been defined in a thesaurus or ontology: synonymous terms and terms in different languages are linked to a single concept. Hierarchical relations between concepts, links between definitions and terms, and other semantic relationships are utilized in the search applications. This process helps to highlight those terms most relevant to the searcher’s query.
Additionally, Collexis’ matching technology is unique. The matching technology computes “distances” between the query and the content items that are being searched, which allows discovery of partially matching documents. Users do not have to construct a complicated (Boolean) search query, but can simply enter a free text search without the risk of getting “no results” due to extensive search term use. In fact, with matching technology, the use of more search text means faster and more accurate results in general.
Yet another aspect that differentiates Collexis is that the computer can easily manipulate the Fingerprints generated by the software. They can be aggregated, associated, clustered, etc. These manipulations also allow Collexis to provide information that goes beyond the level of a single document. Searchers can see information distributed over different documents as well as discernible patterns in a group of documents - e.g., a group of documents written by one author or belonging to a particular semantic category.