Memory-based named entity recognition
Erik F. Tjong Kim Sang · 2002
We apply a memory-based learner to the CoNLL-2002 shared task: language-independent named entity recognition. We use three additional techniques for improving the base performance of the learner: cascading, feature selection and system combination. The overall system is trained with two types of features: words and substrings of words which are relevant for this particular task. It is tested on the two language pairs that were available for this shared task: Spanish and Dutch.