A joint translation model with integrated reordering

This dissertation aims at combining the benefits and to remedy the flaws of the two popular frameworks in statistical machine translation, namely Phrasebased MT and N-gram-based MT. Phrase-based MT advanced the state-of-the art towards translating phrases3 than words. By memorizing phrases, phrasal MT, is able to learn local reorderings, and handling of other local dependencies such as insertions, deletions etc. Inter-phrasal reorderings are handled through the lexicalized reordering model, which remains the state-of-the-art model for reordering in phrase-based SMT till date. However, phrase-based MT has some drawbacks: • Dependencies across phrases are not directly represented in the translation model • Discontinuous phrases cannot be represented and used • The reordering model is not designed to handle long range reorderings • Search and modeling problems require the use of a hard reordering limit • The presence of many different equivalent segmentations increases the search space 3Note that phrases in this thesis mean sequence of words, which may not be linguistic phrases