Annealing Structural Bias in Multilingual Weighted Grammar Induction

  title={Annealing Structural Bias in Multilingual Weighted Grammar Induction},
  author={Noah A. Smith and Jason Eisner},
We first show how a structural locality bias can improve the accuracy of state-of-the-art dependency grammar induction models trained by EM from unannotated examples (Klein and Manning, 2004). Next, by annealing the free parameter that controls this bias, we achieve further improvements. We then describe an alternative kind of structural bias, toward “broken” hypotheses consisting of partial structures over segmented sentences, and show a similar pattern of improvement. We relate this approach… CONTINUE READING
Highly Cited
This paper has 73 citations. REVIEW CITATIONS
54 Citations
31 References
Similar Papers

Similar Papers

Loading similar papers…