Segmentation and Tagging of Oracle Inscriptions Based on Lucene and Dictionary
Segmentation and Part of Speech tagging of Oracle inscriptions are the premise and foundation for establishment of Oracle Corpus and computer-aided Oracle textual research and explication. As for segmentation of Oracle inscriptions, this paper proposes a positive match cut algorithm, which adopts language analyzer based on Lucene and supplemented with Oracle Dictionary. Then the segmented words by the algorithm are tagged. Experiments show that the correct rate is more than 90％.
component Oracle inscriptions segmentation Lucene
KAI Jin-yu LI Na LIU Yong-ge
School of Computer and Information Engineering, Anyang Normal University Oracle Information Processing Key Laboratory Anyang, China
国际会议
南京
英文
608-610
2010-11-01（万方平台首次上网日期，不代表论文的发表时间）