Integrated Text Annotation and Indexing Suite

Language Computer's IndexManager streamlines the process of creating annotated indexes from collections of text in English, Arabic, Chinese, Farsi, and Korean.


When faces with terabytes of text, information consumers need robust tools that will let them annotate -- and index -- large amounts of textual data in a reasonable amount of time. Language Computer's IndexManager delivers the high-performance, distributable indexing capabilities needed to unlock value from even the largest of corpora.

Work only with the files you need.

IndexManager provides access to the state-of-the-art search and filtering capabilities provided by LCC's Ferret and CiceroCustom products.

Drowning in documents? With IndexManager, you can filter documents based on:

  • Document Type
  • Document Creation Date
  • Document Language
  • Keywords or Natural Language Questions
  • Entities from CiceroLite
  • Events from CiceroCustom


Select the right level of annotation.

With IndexManager, users can specify the amount of information that should be associated with an index.

Need to create indexes quickly for CiceroCustom or Ferret? IndexManager's "light" mode can process documents at nearly 80 KB/s using standard hardware.

Need access to even information available from CiceroCustom extractors? IndexManager's "full" indexing mode annotates documents with speeds up to 25 KB/s.

Distributed indexing that's ready when you are.

IndexManager makes it easy to distribute the creation of indexes across networked machines. With one simple interface, users can monitor the progress of indexing, start (or stop) indexing on remote hosts, or even schedule indexing to begin at a later time or date.

IndexManager also simplifies the process of adding new annotations (or documents) to an existing index. Unlike other available annotation tools. there's no need to re-annotate entire indexes: users can simply "update" indexes with just the annotations they need more.

In addition to providing preprocessing capabilities for HTML, SGML, XML, PDF, RTF, and Microsoft Word documents, IndexManager includes built-in WWW harvesting engines which make it easy to download web content or to interface with popular search engines.

Integrating other applications with OpenCicero

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

Hardware / Software Requirements

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

  • 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, 7), Macintosh OS X, Linux (RedHat, CentOS, Ubuntu, etc.), Solaris.
  • Supported Web Service Protocols: SOAP, REST.

Supported Languages and File Formats

IndexManager is available for English, Arabic, Chinese, Farsi, and Korean documents. IndexManager currently processes a wide range of file formats, including Microsoft Word (.doc, .docx), Microsoft Excel (.xls, .xlsx), Microsoft PowerPoint (.ppt, .pptx), XML, PDF, HTML, RTF, and plain text files.

Interested in other languages? Need support for other file formats? Contact us at at for an estimate.

For More Information

For more information about IndexManager, call our product support team at (972) 231-0052, or e-mail us at