摘要
论文提出一种有限分隔最长公共子串算法,将这种算法与改进的最小编辑距离算法相结合实现输入单词与词库内单词的相似度计算。最终将计算结果聚类输出。实验结果表明,应用本文提出的方法进行相似单词查找与单词联想拼写能获得令人满意的结果。另外,我们将所实现的软件与源码公开以供参考。
This paper proposed a limited separation longest common subsequence algorithm.By combined this algorithm with the improved minimum edit distance,the similarity between the input word and the word in a dictionary is calculated.The final clustering searching results are the words that have high similarity value.Experimental results show that the proposed method can obtain satisfying results in similarity word searching and associated word spelling.Besides,we also provide the execute software and source code for reference.
出处
《微计算机信息》
2012年第9期417-418,461,共3页
Control & Automation
基金
基于教师科研的大学生科研实践(No.T11091002)
东南大学教学改革研究与实践项目(No.2010-011)资助
关键词
有限分隔
最长公共子串
最小编辑距离
相似单词
Limited Separation
Longest Common Subsequence
Minimum Edit Distance
Similarity Word