| Summary: | Efficient document classification techniques are crucial to current legal applications, such as case-based reasoning, legal citations, and so on. However, Chinese judgment documents are large and highly complex, so the traditional machine leaning-based classification models are often inefficient to Chinese document classification due to the fact that they fail to incorporate the overall structure and extra domain specific knowledge. In this paper, we propose an ontology-driven knowledge block summarization approach to computing document similarity for Chinese judgment document classification. First, the extra semantic knowledge for Chinese judgment documents is adopted from the perspectives of the top-level ontology and domain-specific ontologies, where how to merge the different kinds of ontologies together in an extensible manner is further represented. Second, the core semantic knowledge residing in Chinese judgment documents can be summarized into knowledge blocks by ontology-based information extraction. Third, we use Word Mover's Distance (WMD) is to calculate the similarity between different knowledge blocks instead of their original Chinese judgment documents. At last, the KNN-based experiments for Chinese judgment document classification were made to illustrate that our approach is more effective in achieving higher classification accuracy and has faster computation speed compared to the original WMD approach.
|
|---|