• Publications
  • Influence
Painless Unsupervised Learning with Features
We show how features can easily be added to standard generative models for unsupervised learning, without requiring complex new training methods. In particular, each component multinomial of aExpand
  • 224
  • 53
  • PDF
Supervised Learning of Complete Morphological Paradigms
We describe a supervised approach to predicting the set of all inflected forms of a lexical item. Our system automatically acquires the orthographic transformation rules of morphological paradigmsExpand
  • 123
  • 14
  • PDF
Why Generative Phrase Models Underperform Surface Heuristics
We investigate why weights from generative models underperform heuristic estimates in phrase-based machine translation. We first propose a simple generative, phrase-based model and verify that itsExpand
  • 86
  • 14
  • PDF
Sampling Alignment Structure under a Bayesian Translation Model
We describe the first tractable Gibbs sampling procedure for estimating phrase pair frequencies under a probabilistic model of phrase alignment. We propose and evaluate two nonparametric priors thatExpand
  • 101
  • 13
  • PDF
Tailoring Word Alignments to Syntactic Machine Translation
Extracting tree transducer rules for syntactic MT systems can be hindered by word alignment errors that violate syntactic correspondences. We propose a novel model for unsupervised word alignmentExpand
  • 127
  • 11
  • PDF
Better Word Alignments with Supervised ITG Models
This work investigates supervised word alignment methods that exploit inversion transduction grammar (ITG) constraints. We consider maximum margin and conditional likelihood objectives, including theExpand
  • 117
  • 9
  • PDF
Adding Interpretable Attention to Neural Translation Models Improves Word Alignment
Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to eachExpand
  • 23
  • 8
  • PDF
The Complexity of Phrase Alignment Problems
Many phrase alignment models operate over the combinatorial space of bijective phrase alignments. We prove that finding an optimal alignment in this space is NP-hard, while computing alignmentExpand
  • 87
  • 7
  • PDF
Variable-Length Word Encodings for Neural Translation Models
Recent work in neural machine translation has shown promising performance, but the most eective architectures do not scale naturally to large vocabulary sizes. We propose and compare threeExpand
  • 34
  • 6
  • PDF
Fast Consensus Decoding over Translation Forests
The minimum Bayes risk (MBR) decoding objective improves BLEU scores for machine translation output relative to the standard Viterbi objective of maximizing model score. However, MBR targeting BLEUExpand
  • 52
  • 5
  • PDF