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 reestimates 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 reanalyzed, and by using Bayesian inference during re-analysis, we show significant improvement over the baseline rules extracted from word-level alignments.

• Type: Journal
• Year: 2009
• Where: EMNLP
• Authors: Ding Liu, Daniel Gildea
• Keywords: EMNLP 2009, Natural Language Processing, Noisy Word-level Alignments, Rule Probabilities, Word-level Alignments