A Stochastic Japanese Morphological Analyzer Using a Forward-DP Backward-A* N-Best Search Algorithm
A Stochastic Japanese Morphological Analyzer Using a Forward-DP Backward-A* N-Best Search Algorithm
复制标题
使用前向 DP 后向 A* N 最佳搜索算法的随机日语形态分析器
DOI：
10.3115/991886.991920
复制
发表时间：
1994
期刊：
影响因子：
--
通讯作者：
M. Nagata
中科院分区：
文献类型：
--
作者：
M. Nagata
我们提出了一种将输入句子分割成单词并为单词分配词性的新方法。它包括一个统计语言模型和一个有效的两遍N-最佳搜索算法。该算法不需要单词之间的分隔符。因此，它适用于书面日语。建议的日语形态分析器达到95.1%的召回率和94.6%的准确率为开放文本时，它是训练和测试的ATR语料库。
We present a novel method for segmenting the input sentence into words and assigning parts of speech to the words. It consists of a statistical language model and an efficient two-pass N-best search algorithm. The algorithm does not require delimiters between words. Thus it is suitable for written Japanese. The proposed Japanese morphological analyzer achieved 95.1% recall and 94.6% precision for open text when it was trained and tested on the ATR Corpus.