Ferret

Precise, High-Performance Question Answering

LCC's question answering technology in Ferret makes it easy to receive direct, relevant answers to natural language questions.

Introduction

The recent explosion of diverse new sources of online documents has underscored the need for high-precision question-answering systems in the analytic environment. Designed specifically for research and intelligence applications, Ferret facilitates information gathering from English, Arabic, Chinese, Farsi, and Korean documents by integrating answers from a state-of-the-art automatic question-answering system with topic-relevant suggestions (known as AutoQUABs) generated from texts.

Ask, don't search.

Don't limit yourself to search results. Ferret allows users to get answers to natural language questions - whether factoid or complex - they need exact answers to.

You shouldn't have to wait for answers.

With Ferret, you won't have to. Ferret employs high-performance document retrieval and answer extraction techniques that ensure you'll get answers in 5 seconds or less.

Learn more about research scenarios with automatically-generated suggestions. [Example]

In addition to answers, Ferret provides uses with sets of automatically-generated question-answer pairs (known as AutoQUABs) which highlight different dimensions of a user's area of interest. Dialogue processing techniques ensure that suggestions stay relevant as users continue to interact with the system.

How it Works

Our technology transforms the standard search into an answer provider, all in the context of a natural, simple and straightforward process.

Released with a pure Java API, Ferret can be easily integrated with various knowledge management and portal resources including search engines, online automated technical support, or customer service dialog systems. A wide range of file formats are supported, including HTML, SGML, XML, PDF, and Microsoft Word documents.

Live Demo

Unfortunately, we don't have a demo of this application available on the web yet. Visit LCC Labs to browse our current selection of demos.

Integrating other applications with OpenCicero

More information about integrating the Ferret into your natural language processing environment with OpenCicero will be made available soon.

Hardware / Software Requirements

LCC's Ferret was designed to run on standard hardware. Have questions about whether it'll run in your environment? E-mail us at support@languagecomputer.com.

  • Minimum Specifications: single-core 2.0 GHz processor , 1 GB of available RAM at run-time.
  • Recommended Specifications: multi-core 2.0 GHz (or better) processor, 2 GB of available RAM.
  • Supported Operating Systems (Desktop Applications): Microsoft Windows (95, 98, XP, Vista), Macintosh OS X, Linux (RedHat, CentOS, Ubuntu, etc.), Solaris.
  • Supported Web Service Protocols: SOAP, REST.

Supported Languages

Ferret is currently available for English, Arabic, and Chinese. Interested in other languages? Contact us at at support@languagecomputer.com for an estimate.

For More Information

For more information about Ferret, call our product support team at (972) 231-0052, or e-mail us at support@languagecomputer.com.