Unsupervised Learning of Morphology for English and Inuktitut

@inproceedings{Johnson2003UnsupervisedLO,
  title={Unsupervised Learning of Morphology for English and Inuktitut},
  author={Howard Johnson and Joel D. Martin},
  booktitle={HLT-NAACL},
  year={2003}
}
We describe a simple unsupervised technique for learning morphology by identifying hubs in an automaton. For our purposes, a hub is a node in a graph with in-degree greater than one and out-degree greater than one. We create a word-trie, transform it into a minimal DFA, then identify hubs. Those hubs mark the boundary between root and suffix, achieving similar performance to more complex mixtures of techniques. 
Highly Cited
This paper has 25 citations. REVIEW CITATIONS
19 Citations
9 References
Similar Papers

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…