Named Entity Recognition is a basic task of Natural Language
Processing and it is basis of some NLP tasks$B!$(Bsuch as machine translation, information retrieval, question answering
and so on. Our work focuses on the named entity recognition of short-text.
The main work in this paper includes:
1. Construction of knowledge base for Chinese short-text oriented
Named Entity Recognition. Based on the analysis of Chinese short-text, we
explore large number of morphological characteristics on Person and Location
name in Chinese short-text. Using these characteristics, we make up short-text
knowledge base respectively for Person and Location name recognition.
2. Combining rules by human knowledge with machine learning to
solve the problem in Chinese short-text oriented Named Entity Recognition. For
different entities$B!$(Bdifferent methods are used. Person and Location name are
recognized with the method of combining expert knowledge with Conditional
Random Fields model.
As the experiments show$B!$(Bwe achieve a good
performance on Chinese short-text oriented Named Entity Recognition.