A Bayesian Model for Learning SCFGs with Discontiguous Rules

@inproceedings{Levenberg2012ABM,
  title={A Bayesian Model for Learning SCFGs with Discontiguous Rules},
  author={Abby D. Levenberg and Chris Dyer and Phil Blunsom},
  booktitle={EMNLP-CoNLL},
  year={2012}
}
We describe a nonparametric model and corresponding inference algorithm for learning Synchronous Context Free Grammar derivations for parallel text. The model employs a Pitman-Yor Process prior which uses a novel base distribution over synchronous grammar rules. Through both synthetic grammar induction and statistical machine translation experiments, we show that our model learns complex translational correspondences— including discontiguous, many-to-many alignments—and produces competitive… CONTINUE READING
Highly Cited
This paper has 31 citations. REVIEW CITATIONS
23 Citations
27 References
Similar Papers

Similar Papers

Loading similar papers…