Evaluation of the Accuracy of the BGLemmatizer
This provides a performance benchmark for Bulgarian NLP tools, but it is incremental as it applies existing methods to a specific language.
The paper evaluated the accuracy of a Bulgarian language lemmatizer, a Java-based GATE plugin, and found it achieved 95% accuracy using statistical methods.
This paper reveals the results of an analysis of the accuracy of developed software for automatic lemmatization for the Bulgarian language. This lemmatization software is written entirely in Java and is distributed as a GATE plugin. Certain statistical methods are used to define the accuracy of this software. The results of the analysis show 95% lemmatization accuracy.