An Unsupervised Method for Uncovering Morphological Chains
Published
2015-03-11
Karthik Narasimhan
,
Regina Barzilay
,
Tommi Jaakkola
Karthik Narasimhan
Massachusetts Institute of Technology
Regina Barzilay
Massachusetts Institute of Technology
Tommi Jaakkola
Massachusetts Institute of Technology
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 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.
PDF (presented at ACL 2015)