Accurate Pronominal and Nominal Coreference Resolution

LCC's CiceroCoref provides accurate pronominal and nominal coreference resolution for English natural language texts.


Language Computer's CiceroCoref increases the utility of entity extraction from natural language texts by identifying multiple references to the same entity, even when different expressions used to refer to the same entity are used.

For instance, when analyzing a large document, one may wish to extract as much information as possible about a particular individual. With LCC's CiceroCoref, information about the individual can be identified more easily since nominal references (e.g. the individual's partial or full name) and pronominal references (e.g. he or she) can be understood to refer to the same individual, resulting in a more complete information extraction solution.

Live Demo

Click below to launch the application. Entities which are coreferential are grouped in the entity pane on the top left.

Integrating other applications with OpenCicero

CiceroCoref can be integrated into your natural language processing environment with OpenCicero.

Hardware / Software Requirements

LCC's CiceroCoref 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

CiceroCoref is currently available for English. Interested in other languages? Contact us at at for an estimate.

For More Information

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