Comparing a Linguistic and a Stochastic Tagger
Comparing a Linguistic and a Stochastic Tagger
复制标题
比较语言标记器和随机标记器
DOI：
--
复制
发表时间：
1997
期刊：
影响因子：
--
通讯作者：
Atro Voutilainen
中科院分区：
文献类型：
--
作者：
C. Samuelsson;Atro Voutilainen
关于自动词性标注的不同方法：在双盲测试中，将基于约束的词法标记器EngCG-2与最新的统计标记器在使用公共标签集的常见消歧任务中进行了比较。实验表明，在剩余歧义量相同的情况下，统计标记器的错误率比基于规则的标注器高一个数量级。此外，还讨论了引发效应对结果的影响和人类注释者之间的分歧这两个相关问题。
Concerning different approaches to automatic PoS tagging: EngCG-2, a constraint-based morphological tagger, is compared in a double-blind test with a state-of-the-art statistical tagger on a common disambiguation task using a common tag set. The experiments show that for the same amount of remaining ambiguity, the error rate of the statistical tagger is one order of magnitude greater than that of the rule-based one. The two related issues of priming effects compromising the results and disagreement between human annotators are also addressed.