基于中文信息处理的古代汉语分词研究

本文在计算机语言处理与古代汉语词汇研究的交叉学科领域进行了新的探索，提出
了一种基于计算机自动分词的词汇处理及量化统计方法，并给出了具体的实现方式。统计结果显示，古代汉语双音词比重自先秦以来以一种平稳的方式增长，该结论与古代汉语词汇研究成果一致。本文提出的方法具有良好的合理性和高效的处理性能，在一定程度上克服了传统人工分词方法的缺陷和不足，因而计算机自然语言处理在古代汉语研究中也有重要的应用价值。1
关键词：计算机自然语言处理；中文信息处理；自动分词

Abstract：A novel interdisciplinary study on the ancient Chinese Vocabulary and computer language processing is present. A computer-based word automatic segmentation for ancient Chinese Vocabulary is proposed and the quantitative statistical method is introduced. The statistical results show that the proportion of the ancient Chinese disyllabic words increases in a stable and progressive way since the Pre-Qin Dynasty, which is consistent with the studies on the ancient Chinese Vocabulary. Therefore, the methods are reasonable and efficient, and overcome defects and deficiencies of the artificial segmentation and statistics methods.
Key words：computer language processing；Chinese information processing；Word
automatic segmentation