arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1503.02335cs.CL
收藏

一种无监督的形态链发现方法

An Unsupervised Method for Uncovering Morphological Chains

Massachusetts Institute of Technology(麻省理工学院)

Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola

摘要:

当今大多数最先进的系统仅基于正交模式产生形态分析。相比之下,我们提出了一个无监督的形态分析模型,整合了词的正字法和语义视图。我们建模构词的形态链,从基础词观察到的话,打破链成亲子关系。我们使用具有词素和词级特征的对数线性模型来预测每个词的可能的父母,包括他们的修饰。每个词的候选父母的有限集合使得对比估计是可行的。我们的模型在阿拉伯语、英语和土耳其语方面始终与五个最先进的系统相匹配或优于它们。

英文摘要:

Most state-of-the-art systems today produce morphological analysis based only on orthographic patterns. In contrast, we propose a model for unsupervised morphological analysis that integrates orthographic and semantic views of words. We model word formation in terms of morphological chains, from base words to the observed words, breaking the chains into parent-child relations. We use log-linear models with morpheme and word-level features to predict possible parents, including their modifications, for each word. The limited set of candidate parents for each word render contrastive estimation feasible. Our model consistently matches or outperforms five state-of-the-art systems on Arabic, English and Turkish.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑