BriefGPT.xyz
Mar, 2015
揭示形态学链的无监督方法
An Unsupervised Method for Uncovering Morphological Chains
HTML
PDF
Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola
TL;DR
通过将词汇的正字法和语义视图相结合，采用基于形态学链的无监督形态学分析模型，使用形态素和单词级别特征的对数线性模型预测可能的父节点来分析阿拉伯语、英语和土耳其语的单词。
Abstract
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
→