An Unsupervised Parts-of-Speech Tagger for the Bangla language

An Unsupervised Parts-of-Speech Tagger for the Bangla language
复制标题

孟加拉语无监督词性标注器

DOI:
--
复制
发表时间:
2008
期刊:
影响因子:
--
通讯作者:
Hammad Ali
Hammad Ali
中科院分区:
--
文献类型:
--
作者:
Hammad Ali

文献摘要

被引文献

相似文献

在本文中,我们介绍了为孟加拉语开发无监督词性(POS)标记器时进行的一些初步实验的结果。我们首先提到该领域所做的一些工作,并介绍尝试无监督方法的理由。然后,我们描述了该项目使用的资源、无监督学习的基本机制,并展示了一些主要结果。然后本文提出了该领域未来的工作方向。
In this paper we present the results of some initial experiments performed in developing an unsupervised Parts-of-Speech (POS) tagger for the Bangla language. We start with mentioning some of the work done in this area, and present the rationale for trying an unsupervised approach. We then describe the resources used for the project, the underlying mechanism for unsupervised learning and present some of the primary results. The paper then suggests future directions of work in this area.