It comprises a set of Java libraries that provide a range of NLP functions: language identification, text segmentation/tokenization, normalization, entity and relationship extraction, and semantic analysis and disambiguation.
The analysis engine uses a finite-state machine approach at multiple levels, which aids its performance characteristics while maintaining a reasonably small footprint.
The behaviour of the system is driven by a set of configurable lexico-semantic resources which describe the characteristics and domain of the processed language.
Supplemental resources have been created that capture additional vocabularies, terminologies, rules and grammars, which may be generic to the language or specific to one or more domains.
LanguageWare can be deployed as a set of UIMA-compliant annotators, Eclipse plug-ins or Web Services.