Friday, March 20, 2009
3:30 PM
CSB 703
Ding Liu
University of Rochester
Bayesian Learning of Phrasal Tree-to-String Templates
We examine the problem of overcoming noisy word-level
alignments when learning tree-to-string translation rules.
Our approach introduces new rules, and re-estimates rule probabilities
using EM. The major obstacles to this approach are the very reasons
that word-alignments are used for rule extraction: the huge
space of possible rules, as well as controlling overfitting.
By carefully controlling which portions of the original alignments
are re-analyzed, and by using Bayesian inference during re-analysis,
we show significant improvement over the baseline rules extracted
from word-level alignments.