Enterprise Search, Text Analytics & Semantics

Enterprise search, text analytics and semantics solutions can help surface vital information — so long as that information has been indexed and analyzed. Most packages, however, rely on rudimentary crawlers or pre-configured content feeds and overlook valuable sources of information. QL2 can deliver content from the deep web, subscription services like Lexis-Nexis and Factiva, email archives, SharePoints, and other document repositories to power your enterprise search engine, text analytics application or semantics tools.

Smarter than a Crawler

QL2 is expert in extracting information from unstructured sources and can reach deep into the nooks and crannies that traditional crawlers can't access. Consider the web. Research suggests that less than 10% of the content available on the Internet is indexed by major search engines. The rest is "invisible" because it's behind a log in screen or can be reached only by filling out a form. QL2 can navigate the web in ways that "brute force" crawlers can't by logging in, filling out forms, collecting and altering cookies, maintaining or erasing session data, and providing specific criteria to generate dynamic pages that otherwise would be inaccessible.

The same is true of intranets. QL2 can process virtually any file type — including PDFs, Word docs, PowerPoint presentations, Outlook and MIME messages, and zipped files — and prepare it for indexing and analysis by your enterprise search engine, text analytics solution or semantics applications.

Documents Delivered to Order

In some cases the challenge isn't collecting more content, but rather filtering out extraneous information. QL2 can extract pertinent sections of a source document before submitting them for indexing and analysis. Not only does this conserve resources, it makes search results and text analytics more relevant.

QL2 can transform content according to the exact specifications required by your enterprise search engine, text analytics software or semantics solution. Whether that's a uniform flat file format, XML, or a custom data feed, QL2 can handle all pre-processing so your search indexing text analytics and semantics endeavors can be carried out quickly and efficiency.

Preferred by Partners

Top enterprise search providers and leading text analytics services depend on QL2 for advanced content discovery, sourcing and transformation. That's why they've partnered with us to make deploying QL2 in conjunction with their service as simple and seamless as possible. QL2 is UIMA-compliant and fully compatible with IBM's WebSphere Information Integrator OmniFind Edition.