Chinese Chunking and Consistency Checking Using Rule-Based Method

Abstract

This paper presents a rule-based chunking approach. Rule-based method does well in analyzing the structure of natural language. In order to avoid the confliction of the rules, we extract a small scale chunking rule set for chunking first. Then we define more rules to check and correct the inconsistency phenomena. We also adopt man-machine interaction method to solve some special language phenomena. Experimental results show that our approach achieves high accuracy.