Chinese Nominal Entity Recognition Based on Inducted Context Patterns
Wenbo Pang, Xiaozhong Fan · 2009
Since whether or not a character sequence refers to an object in real word is determined mostly by its context, the context pattern induction plays an important role in entity recognition, which is an important task in the field of natural language processing (NLP). We present a nominal entity recognition method based on the context pattern induction. It induces high-precision context patterns in an unsupervised way. Then it uses the matched context patterns directly, instead of extracted entities by inducted patterns, as the features of a maximum entropy(ME) based recognition model. The experiments show that the proposed method improves the performance of the high quality nominal entity recognizer, and achieves higher accuracy and recall rate.