首页    期刊浏览 2024年11月28日 星期四
登录注册

文章基本信息

  • 标题:Fast Word Lattice Generation in Morphological Analysis
  • 本地全文:下载
  • 作者:Nobuhiro Kaji ; Masaru Kitsuregawa
  • 期刊名称:人工知能学会論文誌
  • 印刷版ISSN:1346-0714
  • 电子版ISSN:1346-8030
  • 出版年度:2014
  • 卷号:29
  • 期号:2
  • 页码:268-276
  • DOI:10.1527/tjsai.29.268
  • 出版社:The Japanese Society for Artificial Intelligence
  • 摘要:This paper proposes a fast word lattice generation algorithm for Japanese morphological analysis. We conducted experiments on three Japanese data sets to demonstrate that the previously proposed pruning-based algorithm is in fact not efficient enough, and that the pipeline algorithm, which is introduced in this paper, achieves considerable speed-up without loss of accuracy. Moreover, the compactness of the lattice generated by the pipeline algorithm was investigated from both theoretical and empirical perspectives.
  • 关键词:Morphological analysis ; Unknown words ; Word lattice ; Fast algorithm
国家哲学社会科学文献中心版权所有