Simple Type-Level Unsupervised POS Tagging

  title={Simple Type-Level Unsupervised POS Tagging},
  author={Yoong Keok Lee and Aria Haghighi and Regina Barzilay},
Part-of-speech (POS) tag distributions are known to exhibit sparsity — a word is likely to take a single predominant tag in a corpus. Recent research has demonstrated that incorporating this sparsity constraint improves tagging accuracy. However, in existing systems, this expansion come with a steep increase in model complexity. This paper proposes a simple and effective tagging method that directly models tag sparsity and other distributional properties of valid POS tag assignments. In… CONTINUE READING
Highly Cited
This paper has 41 citations. REVIEW CITATIONS
32 Citations
12 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 32 extracted citations

Similar Papers

Loading similar papers…