Improved Backtracking-Forward Algorithm for Maximum Matching Chinese Word Segmentation

Abstract:

In order to improve the accuracy of segmentation, analysis of backtracking-forward maximum matching algorithm exists two defects when dealing with crossing ambiguity, and on this basis, an improved-backtracking forward algorithm for maximum matching algorithm is presented. The improved algorithm is based on the backtracking-forward maximum matching algorithm and adds a module, a chain length of one and 3-words, that can detect and process crossing ambiguity, and taking advantage of counting method, we can merely sort out the defragmenter fields that occurred crossing ambiguity. A number of selected language corpus tests prove that under the premise of the segmentation speed, the improved algorithm can enhance the segmentation accuracy.

• Periodical: Applied Mechanics and Materials (Volumes 536-537)
• Pages: 403-406
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.536-537.403
• Online since: April 2014
• Authors: Hui Li*, Ping Hua Chen
• Keywords: Backtracking-Forward Maximum Matching Algorithm, Chain Length, Crossing Ambiguity, Defragmentation

References

[1] Huili You, Li Yan, Xiao-dong Yang. Computer Engineering and Application, 2011, 47（31）: 125-127. In Chinese.

[2] Tianxia Li, Xinyu Dai, Jiajun Chen. Computer Engineering and Application, 2008, 44（21）: 5-8. In Chinese.

[3] Jingsong Zhang, Jian Yuan. Computer Engineering and Application，2009, 45（22）: 132-134. In Chinese.

[4] Caiqin Zhang, Jian Yuan. Computer Engineering and Design, 2010, 31（11）: 2595-2698. In Chinese.

[5] Yuan Jian, Zhang Jinsong, Ma Liang. Application Research of Computer, 2009, 9（26）: 3321-3323. In Chinese.

[6] Zhen Liang, Yusheng Li. Application Research of Computer, 2010, 31（23）: 5158-5161. In Chinese.