Statistical Machine Translation

Papers and software for statistical machine translation, mostly for historical refererence. See also Wikipedia - Statistical Machine Translation.

• Lopez 2008 - Statistical Machine Translation or Lopez 2007 - A Survey of Statistical Machine Translation (older, but nicer formatting)

• IBM Models
  • Brown et al 1988 - A Statistical Approach to Language Translation Overview paper of the approach
  • Brown et al 1993 - The Mathematics of Statistical Machine Translation: Parameter Estimation Mathematical details of IBM alignment models 1-5
  • IBM's complete system: pdf patent
• Vogel et al 1996 - HMM-Based Word Alignment in Statistical Translation
• Wang & Waibel 1997 - Decoding Algorithm in Statistical Machine Translation
• ReWrite decoder: Germann et al 2001 - Fast Decoding and Optimal Decoding for Machine Translation A* search, hillclimbing, and ILP for decoding for word-based models
• Kumar & Byrne 2003 - A Weighted Finite State Transducer Implementation of the Alignment Template Model for Statistical Machine Translation
• Riedel & Clark 2009 - Revisiting Optimal Decoding for Machine Translation IBM Model 4 Uses an ILP for IBM model 4
• Concavity of IBM model 1: Gimpel & Smith 2012
• Dyer et al 2013 - A Simple, Fast, and Effective Reparameterization of IBM Model 2
• Zenkel et al 2020 - End-to-End Neural Word Alignment Outperforms GIZA++ Not conclusive, since didn't do an extrinsic evaluation in an SMT system. Often, improvements in alignment eror rate (AER) don't translate to better SMT models

• Och et al 2003 - Statistical Phrase-Based Translation
• Och & Ney 2003 - A Systematic Comparison of Various Statistical Alignment Models
• Khoen 2004 - Pharaoh: a beam search decoder for phrase-based statistical machine translation models

• Melamed 2004 - Statistical Machine Translation by Parsing Introduces SCFGs for SMT
• Hiero
  • Chiang 2005 - A Hierarchical Phrase-Based Model for Statistical Machine Translation
  • Chiang 2007 - Hierarchical Phrase-Based Translation
• SAMT

• MERT: Och 2003 - Minimum Error Rate Training in Statistical Machine Translation The standard method for training SMT systems since 2003
• Hypergraph MERT: Kumar et al 2008 - Efficient Minimum Error Rate Training and Minimum Bayes-Risk Decoding for Translation Hypergraphs and Lattices

• Metrics
  • Papineni et al 2001 - BLEU: a Method for Automatic Evaluation of Machine Translation
  • Banerjee & Lavie 2005 - METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments
• Methodology
  • Koehn 2004 - Statistical Significance Tests for Machine Translation Evaluation
  • Clark et al 2011 - Better Hypothesis Testing for Statistical Machine Translation: Controlling for Optimizer Instability

• GIZA++ Open source reimplementation of IBM alignment models Github
• ReWrite Decoder Open source implementation of word-based SMT
• Moses
• cdec Github Old website Older website

• Noisy Channel Model
• Machine Translation