Estimation of Conditional Probabilities With Decision Trees and an Application to Fine-Grained POS Tagging
Estimation of Conditional Probabilities With Decision Trees and an Application to Fine-Grained POS Tagging
复制标题
使用决策树估计条件概率及其在细粒度词性标记中的应用
DOI：
10.3115/1599081.1599179
复制
发表时间：
2008
影响因子：
2.7
通讯作者：
Florian Laws
中科院分区：
文献类型：
--
作者：
Helmut Schmid;Florian Laws
我们提出了一种HMM词性标注方法，特别适合于具有大量细粒度标签的POS标签集。它基于三个思想：（1）将POS标签分割为属性向量，并将HMM的上下文POS概率分解为属性概率的乘积，（2）使用决策树估计上下文概率，以及（3）使用高阶Hacking。在对德国和捷克数据的实验中，我们的标记器优于最先进的POS标记器。
We present a HMM part-of-speech tagging method which is particularly suited for POS tagsets with a large number of fine-grained tags. It is based on three ideas: (1) splitting of the POS tags into attribute vectors and decomposition of the contextual POS probabilities of the HMM into a product of attribute probabilities, (2) estimation of the contextual probabilities with decision trees, and (3) use of high-order HMMs. In experiments on German and Czech data, our tagger outperformed state-of-the-art POS taggers.