Abstract:
The information explosion has created remarkable measure of published information that
is growing at an astounding rate. As information grows at this rate, managing it becomes a
daunting challenge. The key to this test lays in innovation of information extractions
technology that can change unstructured information into organized data to be understood
and controlled by machines. Named Entity Recognition (NER) has the capability to
extract named entities from unstructured documents, ordering them into pre-characterized
semantic classifications and further extracts information in a specific language through use
of defined entities.The research purpose was to analyze named entity recognition
algorithms and use them to identify entities. Experimental research methodology
employed. Kikuyu language was used to provide data for this research. This research
analyzed named entity recognition using Memory Based algorithm and use them to identify
entities. The data collected was used to train a memory-based tool through statistical based
approach. The outcome assisted in solving semantic annotation problem,
development of automatic question-answering systems, semantic web probe, and social
web problem. The output was a named entity recognition that uses memory-based
learning algorithm.
