Phrase Pair Rescoring with Term Weighting for Statistical Machine Translatio.
Bing Zhao, Stephan Vogel, Matthias Eck, Alex Waibel · Empirical Methods in Natural Language Processing · 2004
We propose to score phrase translation pairs for statistical machine translation using term weight based models. These models employ tf.idf to encode the weights of content and non-content words in phrase translation pairs. The translation probability is then modeled by similarity functions defined in a vector space. Two similarity functions are compared. Using these models in a statistical machine translation task shows significant improvements.